modelId
string | author
string | last_modified
unknown | downloads
int64 | likes
int64 | library_name
string | tags
sequence | pipeline_tag
string | createdAt
unknown | card
string |
|---|---|---|---|---|---|---|---|---|---|
EleutherAI/pythia-410m-deduped-v0 | EleutherAI | "2023-07-10T01:31:39Z" | 860 | 6 | transformers | [
"transformers",
"pytorch",
"safetensors",
"gpt_neox",
"text-generation",
"causal-lm",
"pythia",
"pythia_v0",
"en",
"dataset:EleutherAI/the_pile_deduplicated",
"arxiv:2101.00027",
"arxiv:2201.07311",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | "2022-11-01T00:48:44Z" | ---
language:
- en
tags:
- pytorch
- causal-lm
- pythia
- pythia_v0
license: apache-2.0
datasets:
- EleutherAI/the_pile_deduplicated
---
The *Pythia Scaling Suite* is a collection of models developed to facilitate
interpretability research. It contains two sets of eight models of sizes
70M, 160M, 410M, 1B, 1.4B, 2.8B, 6.9B, and 12B. For each size, there are two
models: one trained on the Pile, and one trained on the Pile after the dataset
has been globally deduplicated. All 8 model sizes are trained on the exact
same data, in the exact same order. All Pythia models are available
[on Hugging Face](https://huggingface.co/models?other=pythia).
The Pythia model suite was deliberately designed to promote scientific
research on large language models, especially interpretability research.
Despite not centering downstream performance as a design goal, we find the
models <a href="#evaluations">match or exceed</a> the performance of
similar and same-sized models, such as those in the OPT and GPT-Neo suites.
Please note that all models in the *Pythia* suite were renamed in January
2023. For clarity, a <a href="#naming-convention-and-parameter-count">table
comparing the old and new names</a> is provided in this model card, together
with exact parameter counts.
## Pythia-410M-deduped
### Model Details
- Developed by: [EleutherAI](http://eleuther.ai)
- Model type: Transformer-based Language Model
- Language: English
- Learn more: [Pythia's GitHub repository](https://github.com/EleutherAI/pythia)
for training procedure, config files, and details on how to use.
- Library: [GPT-NeoX](https://github.com/EleutherAI/gpt-neox)
- License: Apache 2.0
- Contact: to ask questions about this model, join the [EleutherAI
Discord](https://discord.gg/zBGx3azzUn), and post them in `#release-discussion`.
Please read the existing *Pythia* documentation before asking about it in the
EleutherAI Discord. For general correspondence: [contact@eleuther.
ai](mailto:contact@eleuther.ai).
<figure>
| Pythia model | Non-Embedding Params | Layers | Model Dim | Heads | Batch Size | Learning Rate | Equivalent Models |
| -----------: | -------------------: | :----: | :-------: | :---: | :--------: | :-------------------: | :--------------------: |
| 70M | 18,915,328 | 6 | 512 | 8 | 2M | 1.0 x 10<sup>-3</sup> | — |
| 160M | 85,056,000 | 12 | 768 | 12 | 4M | 6.0 x 10<sup>-4</sup> | GPT-Neo 125M, OPT-125M |
| 410M | 302,311,424 | 24 | 1024 | 16 | 4M | 3.0 x 10<sup>-4</sup> | OPT-350M |
| 1.0B | 805,736,448 | 16 | 2048 | 8 | 2M | 3.0 x 10<sup>-4</sup> | — |
| 1.4B | 1,208,602,624 | 24 | 2048 | 16 | 4M | 2.0 x 10<sup>-4</sup> | GPT-Neo 1.3B, OPT-1.3B |
| 2.8B | 2,517,652,480 | 32 | 2560 | 32 | 2M | 1.6 x 10<sup>-4</sup> | GPT-Neo 2.7B, OPT-2.7B |
| 6.9B | 6,444,163,072 | 32 | 4096 | 32 | 2M | 1.2 x 10<sup>-4</sup> | OPT-6.7B |
| 12B | 11,327,027,200 | 36 | 5120 | 40 | 2M | 1.2 x 10<sup>-4</sup> | — |
<figcaption>Engineering details for the <i>Pythia Suite</i>. Deduped and
non-deduped models of a given size have the same hyperparameters. “Equivalent”
models have <b>exactly</b> the same architecture, and the same number of
non-embedding parameters.</figcaption>
</figure>
### Uses and Limitations
#### Intended Use
The primary intended use of Pythia is research on the behavior, functionality,
and limitations of large language models. This suite is intended to provide
a controlled setting for performing scientific experiments. To enable the
study of how language models change in the course of training, we provide
143 evenly spaced intermediate checkpoints per model. These checkpoints are
hosted on Hugging Face as branches. Note that branch `143000` corresponds
exactly to the model checkpoint on the `main` branch of each model.
You may also further fine-tune and adapt Pythia-410M-deduped for deployment,
as long as your use is in accordance with the Apache 2.0 license. Pythia
models work with the Hugging Face [Transformers
Library](https://huggingface.co/docs/transformers/index). If you decide to use
pre-trained Pythia-410M-deduped as a basis for your fine-tuned model, please
conduct your own risk and bias assessment.
#### Out-of-scope use
The Pythia Suite is **not** intended for deployment. It is not a in itself
a product and cannot be used for human-facing interactions.
Pythia models are English-language only, and are not suitable for translation
or generating text in other languages.
Pythia-410M-deduped has not been fine-tuned for downstream contexts in which
language models are commonly deployed, such as writing genre prose,
or commercial chatbots. This means Pythia-410M-deduped will **not**
respond to a given prompt the way a product like ChatGPT does. This is because,
unlike this model, ChatGPT was fine-tuned using methods such as Reinforcement
Learning from Human Feedback (RLHF) to better “understand” human instructions.
#### Limitations and biases
The core functionality of a large language model is to take a string of text
and predict the next token. The token deemed statistically most likely by the
model need not produce the most “accurate” text. Never rely on
Pythia-410M-deduped to produce factually accurate output.
This model was trained on [the Pile](https://pile.eleuther.ai/), a dataset
known to contain profanity and texts that are lewd or otherwise offensive.
See [Section 6 of the Pile paper](https://arxiv.org/abs/2101.00027) for a
discussion of documented biases with regards to gender, religion, and race.
Pythia-410M-deduped may produce socially unacceptable or undesirable text,
*even if* the prompt itself does not include anything explicitly offensive.
If you plan on using text generated through, for example, the Hosted Inference
API, we recommend having a human curate the outputs of this language model
before presenting it to other people. Please inform your audience that the
text was generated by Pythia-410M-deduped.
### Quickstart
Pythia models can be loaded and used via the following code, demonstrated here
for the third `pythia-70m-deduped` checkpoint:
```python
from transformers import GPTNeoXForCausalLM, AutoTokenizer
model = GPTNeoXForCausalLM.from_pretrained(
"EleutherAI/pythia-70m-deduped",
revision="step3000",
cache_dir="./pythia-70m-deduped/step3000",
)
tokenizer = AutoTokenizer.from_pretrained(
"EleutherAI/pythia-70m-deduped",
revision="step3000",
cache_dir="./pythia-70m-deduped/step3000",
)
inputs = tokenizer("Hello, I am", return_tensors="pt")
tokens = model.generate(**inputs)
tokenizer.decode(tokens[0])
```
Revision/branch `step143000` corresponds exactly to the model checkpoint on
the `main` branch of each model.<br>
For more information on how to use all Pythia models, see [documentation on
GitHub](https://github.com/EleutherAI/pythia).
### Training
#### Training data
Pythia-410M-deduped was trained on the Pile **after the dataset has been
globally deduplicated**.<br>
[The Pile](https://pile.eleuther.ai/) is a 825GiB general-purpose dataset in
English. It was created by EleutherAI specifically for training large language
models. It contains texts from 22 diverse sources, roughly broken down into
five categories: academic writing (e.g. arXiv), internet (e.g. CommonCrawl),
prose (e.g. Project Gutenberg), dialogue (e.g. YouTube subtitles), and
miscellaneous (e.g. GitHub, Enron Emails). See [the Pile
paper](https://arxiv.org/abs/2101.00027) for a breakdown of all data sources,
methodology, and a discussion of ethical implications. Consult [the
datasheet](https://arxiv.org/abs/2201.07311) for more detailed documentation
about the Pile and its component datasets. The Pile can be downloaded from
the [official website](https://pile.eleuther.ai/), or from a [community
mirror](https://the-eye.eu/public/AI/pile/).
#### Training procedure
All models were trained on the exact same data, in the exact same order. Each
model saw 299,892,736,000 tokens during training, and 143 checkpoints for each
model are saved every 2,097,152,000 tokens, spaced evenly throughout training.
This corresponds to training for just under 1 epoch on the Pile for
non-deduplicated models, and about 1.5 epochs on the deduplicated Pile.
All *Pythia* models trained for the equivalent of 143000 steps at a batch size
of 2,097,152 tokens. Two batch sizes were used: 2M and 4M. Models with a batch
size of 4M tokens listed were originally trained for 71500 steps instead, with
checkpoints every 500 steps. The checkpoints on Hugging Face are renamed for
consistency with all 2M batch models, so `step1000` is the first checkpoint
for `pythia-1.4b` that was saved (corresponding to step 500 in training), and
`step1000` is likewise the first `pythia-6.9b` checkpoint that was saved
(corresponding to 1000 “actual” steps).<br>
See [GitHub](https://github.com/EleutherAI/pythia) for more details on training
procedure, including [how to reproduce
it](https://github.com/EleutherAI/pythia/blob/main/README.md#reproducing-training).<br>
Pythia uses the same tokenizer as [GPT-NeoX-
20B](https://huggingface.co/EleutherAI/gpt-neox-20b).
### Evaluations
All 16 *Pythia* models were evaluated using the [LM Evaluation
Harness](https://github.com/EleutherAI/lm-evaluation-harness). You can access
the results by model and step at `results/json/*` in the [GitHub
repository](https://github.com/EleutherAI/pythia/tree/main/results/json).<br>
Expand the sections below to see plots of evaluation results for all
Pythia and Pythia-deduped models compared with OPT and BLOOM.
<details>
<summary>LAMBADA – OpenAI</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/lambada_openai.png" style="width:auto"/>
</details>
<details>
<summary>Physical Interaction: Question Answering (PIQA)</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/piqa.png" style="width:auto"/>
</details>
<details>
<summary>WinoGrande</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/winogrande.png" style="width:auto"/>
</details>
<details>
<summary>AI2 Reasoning Challenge – Challenge Set</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/arc_challenge.png" style="width:auto"/>
</details>
<details>
<summary>SciQ</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/sciq.png" style="width:auto"/>
</details>
### Naming convention and parameter count
*Pythia* models were renamed in January 2023. It is possible that the old
naming convention still persists in some documentation by accident. The
current naming convention (70M, 160M, etc.) is based on total parameter count.
<figure style="width:32em">
| current Pythia suffix | old suffix | total params | non-embedding params |
| --------------------: | ---------: | -------------: | -------------------: |
| 70M | 19M | 70,426,624 | 18,915,328 |
| 160M | 125M | 162,322,944 | 85,056,000 |
| 410M | 350M | 405,334,016 | 302,311,424 |
| 1B | 800M | 1,011,781,632 | 805,736,448 |
| 1.4B | 1.3B | 1,414,647,808 | 1,208,602,624 |
| 2.8B | 2.7B | 2,775,208,960 | 2,517,652,480 |
| 6.9B | 6.7B | 6,857,302,016 | 6,444,163,072 |
| 12B | 13B | 11,846,072,320 | 11,327,027,200 |
</figure> |
ALM-AHME/convnextv2-large-1k-224-finetuned-LungCancer-Classification-LC25000-AH-60-20-20 | ALM-AHME | "2023-07-10T01:24:21Z" | 6 | 1 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"convnextv2",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"license:apache-2.0",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | "2023-07-09T21:54:01Z" | ---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
metrics:
- accuracy
model-index:
- name: convnextv2-large-1k-224-finetuned-LungCancer-Classification-LC25000-AH-60-20-20
results:
- task:
name: Image Classification
type: image-classification
dataset:
name: imagefolder
type: imagefolder
config: Augmented-Final
split: train
args: Augmented-Final
metrics:
- name: Accuracy
type: accuracy
value: 0.9996666666666667
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# convnextv2-large-1k-224-finetuned-LungCancer-Classification-LC25000-AH-60-20-20
This model is a fine-tuned version of [facebook/convnextv2-large-1k-224](https://huggingface.co/facebook/convnextv2-large-1k-224) on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0043
- Accuracy: 0.9997
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.9
- num_epochs: 12
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 0.4332 | 1.0 | 281 | 0.3824 | 0.947 |
| 0.1558 | 2.0 | 563 | 0.1292 | 0.9737 |
| 0.1161 | 3.0 | 844 | 0.0556 | 0.9887 |
| 0.2337 | 4.0 | 1126 | 0.0683 | 0.982 |
| 0.1285 | 5.0 | 1407 | 0.0293 | 0.9923 |
| 0.047 | 6.0 | 1689 | 0.0987 | 0.975 |
| 0.0741 | 7.0 | 1970 | 0.0373 | 0.988 |
| 0.153 | 8.0 | 2252 | 0.0043 | 0.9997 |
| 0.0244 | 9.0 | 2533 | 0.0696 | 0.981 |
| 0.0646 | 10.0 | 2815 | 0.0120 | 0.995 |
| 0.0025 | 11.0 | 3096 | 0.0076 | 0.9977 |
| 0.0611 | 11.98 | 3372 | 0.0024 | 0.9997 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
NasimB/gpt2-concat-cbt-rarity-2k-p3k-rerun | NasimB | "2023-07-10T01:14:18Z" | 5 | 0 | transformers | [
"transformers",
"pytorch",
"gpt2",
"text-generation",
"generated_from_trainer",
"dataset:generator",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | "2023-07-09T22:53:18Z" | ---
license: mit
tags:
- generated_from_trainer
datasets:
- generator
model-index:
- name: gpt2-concat-cbt-rarity-2k-p3k-rerun
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# gpt2-concat-cbt-rarity-2k-p3k-rerun
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 3.0111
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 7
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 6.7193 | 0.29 | 500 | 5.6348 |
| 5.3717 | 0.58 | 1000 | 5.2023 |
| 5.0316 | 0.87 | 1500 | 4.9479 |
| 4.7526 | 1.17 | 2000 | 4.8054 |
| 4.5908 | 1.46 | 2500 | 4.6881 |
| 4.4855 | 1.75 | 3000 | 4.5743 |
| 4.37 | 2.04 | 3500 | 4.4982 |
| 4.1665 | 2.33 | 4000 | 4.4536 |
| 4.1433 | 2.62 | 4500 | 4.3994 |
| 4.1049 | 2.91 | 5000 | 4.3436 |
| 3.9129 | 3.21 | 5500 | 4.3424 |
| 3.8605 | 3.5 | 6000 | 4.3136 |
| 3.8444 | 3.79 | 6500 | 4.2788 |
| 3.7551 | 4.08 | 7000 | 4.2807 |
| 3.5722 | 4.37 | 7500 | 4.2752 |
| 3.58 | 4.66 | 8000 | 4.2599 |
| 3.5691 | 4.95 | 8500 | 4.2378 |
| 3.3607 | 5.24 | 9000 | 4.2659 |
| 3.3218 | 5.54 | 9500 | 4.2623 |
| 3.3249 | 5.83 | 10000 | 4.2549 |
| 3.2621 | 6.12 | 10500 | 4.2656 |
| 3.1746 | 6.41 | 11000 | 4.2682 |
| 3.1689 | 6.7 | 11500 | 4.2679 |
| 3.17 | 6.99 | 12000 | 4.2677 |
### Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
|
Porcelalina/Melanietest | Porcelalina | "2023-07-10T00:50:41Z" | 0 | 0 | null | [
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"arxiv:2207.12598",
"arxiv:2112.10752",
"arxiv:2103.00020",
"arxiv:2205.11487",
"arxiv:1910.09700",
"license:creativeml-openrail-m",
"region:us"
] | text-to-image | "2023-07-09T13:45:36Z" | ---
license: creativeml-openrail-m
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
inference: true
extra_gated_prompt: |-
This model is open access and available to all, with a CreativeML OpenRAIL-M license further specifying rights and usage.
The CreativeML OpenRAIL License specifies:
1. You can't use the model to deliberately produce nor share illegal or harmful outputs or content
2. CompVis claims no rights on the outputs you generate, you are free to use them and are accountable for their use which must not go against the provisions set in the license
3. You may re-distribute the weights and use the model commercially and/or as a service. If you do, please be aware you have to include the same use restrictions as the ones in the license and share a copy of the CreativeML OpenRAIL-M to all your users (please read the license entirely and carefully)
Please read the full license carefully here: https://huggingface.co/spaces/CompVis/stable-diffusion-license
extra_gated_heading: Please read the LICENSE to access this model
---
# Stable Diffusion v1-5 Model Card
Stable Diffusion is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input.
For more information about how Stable Diffusion functions, please have a look at [🤗's Stable Diffusion blog](https://huggingface.co/blog/stable_diffusion).
The **Stable-Diffusion-v1-5** checkpoint was initialized with the weights of the [Stable-Diffusion-v1-2](https:/steps/huggingface.co/CompVis/stable-diffusion-v1-2)
checkpoint and subsequently fine-tuned on 595k steps at resolution 512x512 on "laion-aesthetics v2 5+" and 10% dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598).
You can use this both with the [🧨Diffusers library](https://github.com/huggingface/diffusers) and the [RunwayML GitHub repository](https://github.com/runwayml/stable-diffusion).
### Diffusers
```py
from diffusers import StableDiffusionPipeline
import torch
model_id = "runwayml/stable-diffusion-v1-5"
pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
pipe = pipe.to("cuda")
prompt = "a photo of an astronaut riding a horse on mars"
image = pipe(prompt).images[0]
image.save("astronaut_rides_horse.png")
```
For more detailed instructions, use-cases and examples in JAX follow the instructions [here](https://github.com/huggingface/diffusers#text-to-image-generation-with-stable-diffusion)
### Original GitHub Repository
1. Download the weights
- [v1-5-pruned-emaonly.ckpt](https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned-emaonly.ckpt) - 4.27GB, ema-only weight. uses less VRAM - suitable for inference
- [v1-5-pruned.ckpt](https://huggingface.co/runwayml/stable-diffusion-v1-5/resolve/main/v1-5-pruned.ckpt) - 7.7GB, ema+non-ema weights. uses more VRAM - suitable for fine-tuning
2. Follow instructions [here](https://github.com/runwayml/stable-diffusion).
## Model Details
- **Developed by:** Robin Rombach, Patrick Esser
- **Model type:** Diffusion-based text-to-image generation model
- **Language(s):** English
- **License:** [The CreativeML OpenRAIL M license](https://huggingface.co/spaces/CompVis/stable-diffusion-license) is an [Open RAIL M license](https://www.licenses.ai/blog/2022/8/18/naming-convention-of-responsible-ai-licenses), adapted from the work that [BigScience](https://bigscience.huggingface.co/) and [the RAIL Initiative](https://www.licenses.ai/) are jointly carrying in the area of responsible AI licensing. See also [the article about the BLOOM Open RAIL license](https://bigscience.huggingface.co/blog/the-bigscience-rail-license) on which our license is based.
- **Model Description:** This is a model that can be used to generate and modify images based on text prompts. It is a [Latent Diffusion Model](https://arxiv.org/abs/2112.10752) that uses a fixed, pretrained text encoder ([CLIP ViT-L/14](https://arxiv.org/abs/2103.00020)) as suggested in the [Imagen paper](https://arxiv.org/abs/2205.11487).
- **Resources for more information:** [GitHub Repository](https://github.com/CompVis/stable-diffusion), [Paper](https://arxiv.org/abs/2112.10752).
- **Cite as:**
@InProceedings{Rombach_2022_CVPR,
author = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn},
title = {High-Resolution Image Synthesis With Latent Diffusion Models},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2022},
pages = {10684-10695}
}
# Uses
## Direct Use
The model is intended for research purposes only. Possible research areas and
tasks include
- Safe deployment of models which have the potential to generate harmful content.
- Probing and understanding the limitations and biases of generative models.
- Generation of artworks and use in design and other artistic processes.
- Applications in educational or creative tools.
- Research on generative models.
Excluded uses are described below.
### Misuse, Malicious Use, and Out-of-Scope Use
_Note: This section is taken from the [DALLE-MINI model card](https://huggingface.co/dalle-mini/dalle-mini), but applies in the same way to Stable Diffusion v1_.
The model should not be used to intentionally create or disseminate images that create hostile or alienating environments for people. This includes generating images that people would foreseeably find disturbing, distressing, or offensive; or content that propagates historical or current stereotypes.
#### Out-of-Scope Use
The model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model.
#### Misuse and Malicious Use
Using the model to generate content that is cruel to individuals is a misuse of this model. This includes, but is not limited to:
- Generating demeaning, dehumanizing, or otherwise harmful representations of people or their environments, cultures, religions, etc.
- Intentionally promoting or propagating discriminatory content or harmful stereotypes.
- Impersonating individuals without their consent.
- Sexual content without consent of the people who might see it.
- Mis- and disinformation
- Representations of egregious violence and gore
- Sharing of copyrighted or licensed material in violation of its terms of use.
- Sharing content that is an alteration of copyrighted or licensed material in violation of its terms of use.
## Limitations and Bias
### Limitations
- The model does not achieve perfect photorealism
- The model cannot render legible text
- The model does not perform well on more difficult tasks which involve compositionality, such as rendering an image corresponding to “A red cube on top of a blue sphere”
- Faces and people in general may not be generated properly.
- The model was trained mainly with English captions and will not work as well in other languages.
- The autoencoding part of the model is lossy
- The model was trained on a large-scale dataset
[LAION-5B](https://laion.ai/blog/laion-5b/) which contains adult material
and is not fit for product use without additional safety mechanisms and
considerations.
- No additional measures were used to deduplicate the dataset. As a result, we observe some degree of memorization for images that are duplicated in the training data.
The training data can be searched at [https://rom1504.github.io/clip-retrieval/](https://rom1504.github.io/clip-retrieval/) to possibly assist in the detection of memorized images.
### Bias
While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases.
Stable Diffusion v1 was trained on subsets of [LAION-2B(en)](https://laion.ai/blog/laion-5b/),
which consists of images that are primarily limited to English descriptions.
Texts and images from communities and cultures that use other languages are likely to be insufficiently accounted for.
This affects the overall output of the model, as white and western cultures are often set as the default. Further, the
ability of the model to generate content with non-English prompts is significantly worse than with English-language prompts.
### Safety Module
The intended use of this model is with the [Safety Checker](https://github.com/huggingface/diffusers/blob/main/src/diffusers/pipelines/stable_diffusion/safety_checker.py) in Diffusers.
This checker works by checking model outputs against known hard-coded NSFW concepts.
The concepts are intentionally hidden to reduce the likelihood of reverse-engineering this filter.
Specifically, the checker compares the class probability of harmful concepts in the embedding space of the `CLIPTextModel` *after generation* of the images.
The concepts are passed into the model with the generated image and compared to a hand-engineered weight for each NSFW concept.
## Training
**Training Data**
The model developers used the following dataset for training the model:
- LAION-2B (en) and subsets thereof (see next section)
**Training Procedure**
Stable Diffusion v1-5 is a latent diffusion model which combines an autoencoder with a diffusion model that is trained in the latent space of the autoencoder. During training,
- Images are encoded through an encoder, which turns images into latent representations. The autoencoder uses a relative downsampling factor of 8 and maps images of shape H x W x 3 to latents of shape H/f x W/f x 4
- Text prompts are encoded through a ViT-L/14 text-encoder.
- The non-pooled output of the text encoder is fed into the UNet backbone of the latent diffusion model via cross-attention.
- The loss is a reconstruction objective between the noise that was added to the latent and the prediction made by the UNet.
Currently six Stable Diffusion checkpoints are provided, which were trained as follows.
- [`stable-diffusion-v1-1`](https://huggingface.co/CompVis/stable-diffusion-v1-1): 237,000 steps at resolution `256x256` on [laion2B-en](https://huggingface.co/datasets/laion/laion2B-en).
194,000 steps at resolution `512x512` on [laion-high-resolution](https://huggingface.co/datasets/laion/laion-high-resolution) (170M examples from LAION-5B with resolution `>= 1024x1024`).
- [`stable-diffusion-v1-2`](https://huggingface.co/CompVis/stable-diffusion-v1-2): Resumed from `stable-diffusion-v1-1`.
515,000 steps at resolution `512x512` on "laion-improved-aesthetics" (a subset of laion2B-en,
filtered to images with an original size `>= 512x512`, estimated aesthetics score `> 5.0`, and an estimated watermark probability `< 0.5`. The watermark estimate is from the LAION-5B metadata, the aesthetics score is estimated using an [improved aesthetics estimator](https://github.com/christophschuhmann/improved-aesthetic-predictor)).
- [`stable-diffusion-v1-3`](https://huggingface.co/CompVis/stable-diffusion-v1-3): Resumed from `stable-diffusion-v1-2` - 195,000 steps at resolution `512x512` on "laion-improved-aesthetics" and 10 % dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598).
- [`stable-diffusion-v1-4`](https://huggingface.co/CompVis/stable-diffusion-v1-4) Resumed from `stable-diffusion-v1-2` - 225,000 steps at resolution `512x512` on "laion-aesthetics v2 5+" and 10 % dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598).
- [`stable-diffusion-v1-5`](https://huggingface.co/runwayml/stable-diffusion-v1-5) Resumed from `stable-diffusion-v1-2` - 595,000 steps at resolution `512x512` on "laion-aesthetics v2 5+" and 10 % dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598).
- [`stable-diffusion-inpainting`](https://huggingface.co/runwayml/stable-diffusion-inpainting) Resumed from `stable-diffusion-v1-5` - then 440,000 steps of inpainting training at resolution 512x512 on “laion-aesthetics v2 5+” and 10% dropping of the text-conditioning. For inpainting, the UNet has 5 additional input channels (4 for the encoded masked-image and 1 for the mask itself) whose weights were zero-initialized after restoring the non-inpainting checkpoint. During training, we generate synthetic masks and in 25% mask everything.
- **Hardware:** 32 x 8 x A100 GPUs
- **Optimizer:** AdamW
- **Gradient Accumulations**: 2
- **Batch:** 32 x 8 x 2 x 4 = 2048
- **Learning rate:** warmup to 0.0001 for 10,000 steps and then kept constant
## Evaluation Results
Evaluations with different classifier-free guidance scales (1.5, 2.0, 3.0, 4.0,
5.0, 6.0, 7.0, 8.0) and 50 PNDM/PLMS sampling
steps show the relative improvements of the checkpoints:
Evaluated using 50 PLMS steps and 10000 random prompts from the COCO2017 validation set, evaluated at 512x512 resolution. Not optimized for FID scores.
## Environmental Impact
**Stable Diffusion v1** **Estimated Emissions**
Based on that information, we estimate the following CO2 emissions using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700). The hardware, runtime, cloud provider, and compute region were utilized to estimate the carbon impact.
- **Hardware Type:** A100 PCIe 40GB
- **Hours used:** 150000
- **Cloud Provider:** AWS
- **Compute Region:** US-east
- **Carbon Emitted (Power consumption x Time x Carbon produced based on location of power grid):** 11250 kg CO2 eq.
## Citation
```bibtex
@InProceedings{Rombach_2022_CVPR,
author = {Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj\"orn},
title = {High-Resolution Image Synthesis With Latent Diffusion Models},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2022},
pages = {10684-10695}
}
```
*This model card was written by: Robin Rombach and Patrick Esser and is based on the [DALL-E Mini model card](https://huggingface.co/dalle-mini/dalle-mini).* |
crisU8/bert-finetuned-ner-clinical-trials-2 | crisU8 | "2023-07-10T00:48:07Z" | 101 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"roberta",
"token-classification",
"generated_from_trainer",
"license:cc-by-nc-4.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | token-classification | "2023-07-10T00:29:03Z" | ---
license: cc-by-nc-4.0
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: bert-finetuned-ner-clinical-trials-2
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-finetuned-ner-clinical-trials-2
This model is a fine-tuned version of [lcampillos/roberta-es-clinical-trials-ner](https://huggingface.co/lcampillos/roberta-es-clinical-trials-ner) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3516
- Precision: 0.7329
- Recall: 0.7755
- F1: 0.7536
- Accuracy: 0.9141
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
### Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:------:|:--------:|
| 0.158 | 1.0 | 502 | 0.3028 | 0.7104 | 0.7700 | 0.7390 | 0.9144 |
| 0.1061 | 2.0 | 1004 | 0.3578 | 0.7020 | 0.7772 | 0.7377 | 0.9094 |
| 0.123 | 3.0 | 1506 | 0.3296 | 0.7237 | 0.7750 | 0.7485 | 0.9139 |
| 0.1007 | 4.0 | 2008 | 0.3516 | 0.7329 | 0.7755 | 0.7536 | 0.9141 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Hedayat-Abrishami/Reinforce-2 | Hedayat-Abrishami | "2023-07-10T00:32:49Z" | 0 | 0 | null | [
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] | reinforcement-learning | "2023-07-10T00:32:36Z" | ---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-2
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 69.30 +/- 55.81
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **Pixelcopter-PLE-v0**
This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
LongshenOu/lyric-trans-en2zh | LongshenOu | "2023-07-10T00:16:10Z" | 31 | 0 | transformers | [
"transformers",
"pytorch",
"mbart",
"license:cc-by-nc-sa-4.0",
"endpoints_compatible",
"region:us"
] | null | "2023-07-10T00:07:39Z" | ---
license: cc-by-nc-sa-4.0
---
|
Ragnaldo/distilbert-base-uncased-finetuned-cola | Ragnaldo | "2023-07-10T00:03:55Z" | 61 | 0 | transformers | [
"transformers",
"tf",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | "2023-07-09T22:47:08Z" | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: Ragnaldo/distilbert-base-uncased-finetuned-cola
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# Ragnaldo/distilbert-base-uncased-finetuned-cola
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.1935
- Validation Loss: 0.5461
- Train Matthews Correlation: 0.5387
- Epoch: 2
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1602, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Train Matthews Correlation | Epoch |
|:----------:|:---------------:|:--------------------------:|:-----:|
| 0.5260 | 0.4716 | 0.4547 | 0 |
| 0.3255 | 0.5045 | 0.4972 | 1 |
| 0.1935 | 0.5461 | 0.5387 | 2 |
### Framework versions
- Transformers 4.30.2
- TensorFlow 2.12.0
- Datasets 2.13.1
- Tokenizers 0.13.3
|
bochen0909/distilhubert-finetuned-gtzan | bochen0909 | "2023-07-09T23:30:38Z" | 161 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"hubert",
"audio-classification",
"generated_from_trainer",
"dataset:marsyas/gtzan",
"base_model:ntu-spml/distilhubert",
"base_model:finetune:ntu-spml/distilhubert",
"license:apache-2.0",
"model-index",
"endpoints_compatible",
"region:us"
] | audio-classification | "2023-07-09T05:16:29Z" | ---
license: apache-2.0
base_model: ntu-spml/distilhubert
tags:
- generated_from_trainer
datasets:
- marsyas/gtzan
metrics:
- accuracy
model-index:
- name: distilhubert-finetuned-gtzan
results:
- task:
name: Audio Classification
type: audio-classification
dataset:
name: GTZAN
type: marsyas/gtzan
config: all
split: train
args: all
metrics:
- name: Accuracy
type: accuracy
value: 0.84
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilhubert-finetuned-gtzan
This model is a fine-tuned version of [ntu-spml/distilhubert](https://huggingface.co/ntu-spml/distilhubert) on the GTZAN dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5454
- Accuracy: 0.84
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 12
- eval_batch_size: 12
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|:-------------:|:-----:|:----:|:---------------:|:--------:|
| 2.0594 | 1.0 | 75 | 1.9411 | 0.59 |
| 1.4643 | 2.0 | 150 | 1.3450 | 0.72 |
| 1.1926 | 3.0 | 225 | 1.1038 | 0.7 |
| 0.9126 | 4.0 | 300 | 0.9084 | 0.71 |
| 0.6716 | 5.0 | 375 | 0.7864 | 0.77 |
| 0.5595 | 6.0 | 450 | 0.6647 | 0.8 |
| 0.4235 | 7.0 | 525 | 0.6587 | 0.8 |
| 0.3118 | 8.0 | 600 | 0.6317 | 0.81 |
| 0.2283 | 9.0 | 675 | 0.5696 | 0.84 |
| 0.264 | 10.0 | 750 | 0.5454 | 0.84 |
### Framework versions
- Transformers 4.31.0.dev0
- Pytorch 1.13.1
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Milanesa16/MikiMatsubara | Milanesa16 | "2023-07-09T22:53:33Z" | 0 | 1 | null | [
"music",
"model",
"rvc",
"ja",
"license:openrail",
"region:us"
] | null | "2023-07-09T22:33:27Z" | ---
license: openrail
language:
- ja
tags:
- music
- model
- rvc
--- |
tbooy/ppo-Huggy | tbooy | "2023-07-09T22:51:45Z" | 0 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] | reinforcement-learning | "2023-07-09T22:51:40Z" | ---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: tbooy/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
skywalker7/q-FrozenLake-v1-4x4-noSlippery | skywalker7 | "2023-07-09T22:44:29Z" | 0 | 0 | null | [
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | "2023-07-09T22:44:27Z" | ---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-noSlippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="skywalker7/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
saintzeno/rl_course_vizdoom_health_gathering_supreme | saintzeno | "2023-07-09T22:30:27Z" | 0 | 0 | sample-factory | [
"sample-factory",
"tensorboard",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | "2023-07-09T22:30:22Z" | ---
library_name: sample-factory
tags:
- deep-reinforcement-learning
- reinforcement-learning
- sample-factory
model-index:
- name: APPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: doom_health_gathering_supreme
type: doom_health_gathering_supreme
metrics:
- type: mean_reward
value: 9.89 +/- 3.21
name: mean_reward
verified: false
---
A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment.
This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
## Downloading the model
After installing Sample-Factory, download the model with:
```
python -m sample_factory.huggingface.load_from_hub -r saintzeno/rl_course_vizdoom_health_gathering_supreme
```
## Using the model
To run the model after download, use the `enjoy` script corresponding to this environment:
```
python -m .usr.local.lib.python3.10.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
```
You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
## Training with this model
To continue training with this model, use the `train` script corresponding to this environment:
```
python -m .usr.local.lib.python3.10.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
```
Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
|
NasimB/gpt2-concat-mod-datatsets-rarity-all-iorder-no-cut-repetition | NasimB | "2023-07-09T22:29:37Z" | 5 | 0 | transformers | [
"transformers",
"pytorch",
"gpt2",
"text-generation",
"generated_from_trainer",
"dataset:generator",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | "2023-07-09T20:40:54Z" | ---
license: mit
tags:
- generated_from_trainer
datasets:
- generator
model-index:
- name: gpt2-concat-mod-datatsets-rarity-all-iorder-no-cut-repetition
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# gpt2-concat-mod-datatsets-rarity-all-iorder-no-cut-repetition
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 3.2189
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 6
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 6.734 | 0.3 | 500 | 5.7011 |
| 5.3923 | 0.6 | 1000 | 5.2709 |
| 5.0404 | 0.9 | 1500 | 5.0055 |
| 4.7561 | 1.21 | 2000 | 4.8552 |
| 4.6189 | 1.51 | 2500 | 4.7257 |
| 4.5064 | 1.81 | 3000 | 4.6217 |
| 4.3497 | 2.11 | 3500 | 4.5593 |
| 4.1924 | 2.41 | 4000 | 4.5086 |
| 4.1669 | 2.71 | 4500 | 4.4446 |
| 4.102 | 3.01 | 5000 | 4.4099 |
| 3.8642 | 3.32 | 5500 | 4.4021 |
| 3.8619 | 3.62 | 6000 | 4.3641 |
| 3.8392 | 3.92 | 6500 | 4.3356 |
| 3.6347 | 4.22 | 7000 | 4.3605 |
| 3.5759 | 4.52 | 7500 | 4.3424 |
| 3.5613 | 4.82 | 8000 | 4.3281 |
| 3.4782 | 5.12 | 8500 | 4.3392 |
| 3.3739 | 5.42 | 9000 | 4.3409 |
| 3.3737 | 5.73 | 9500 | 4.3415 |
### Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
|
Raizel123/Renitalora | Raizel123 | "2023-07-09T22:25:03Z" | 0 | 0 | null | [
"license:creativeml-openrail-m",
"region:us"
] | null | "2023-07-09T22:22:22Z" | ---
license: creativeml-openrail-m
---
|
Gustavosta/MagicPrompt-Stable-Diffusion | Gustavosta | "2023-07-09T22:10:48Z" | 139,564 | 718 | transformers | [
"transformers",
"pytorch",
"coreml",
"safetensors",
"gpt2",
"text-generation",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | "2022-09-17T22:34:07Z" | ---
license: mit
---
# MagicPrompt - Stable Diffusion
This is a model from the MagicPrompt series of models, which are [GPT-2](https://huggingface.co/gpt2) models intended to generate prompt texts for imaging AIs, in this case: [Stable Diffusion](https://huggingface.co/CompVis/stable-diffusion).
## 🖼️ Here's an example:
<img src="https://files.catbox.moe/ac3jq7.png">
This model was trained with 150,000 steps and a set of about 80,000 data filtered and extracted from the image finder for Stable Diffusion: "[Lexica.art](https://lexica.art/)". It was a little difficult to extract the data, since the search engine still doesn't have a public API without being protected by cloudflare, but if you want to take a look at the original dataset, you can have a look here: [datasets/Gustavosta/Stable-Diffusion-Prompts](https://huggingface.co/datasets/Gustavosta/Stable-Diffusion-Prompts).
If you want to test the model with a demo, you can go to: "[spaces/Gustavosta/MagicPrompt-Stable-Diffusion](https://huggingface.co/spaces/Gustavosta/MagicPrompt-Stable-Diffusion)".
## 💻 You can see other MagicPrompt models:
- For Dall-E 2: [Gustavosta/MagicPrompt-Dalle](https://huggingface.co/Gustavosta/MagicPrompt-Dalle)
- For Midjourney: [Gustavosta/MagicPrompt-Midourney](https://huggingface.co/Gustavosta/MagicPrompt-Midjourney) **[⚠️ In progress]**
- MagicPrompt full: [Gustavosta/MagicPrompt](https://huggingface.co/Gustavosta/MagicPrompt) **[⚠️ In progress]**
## ⚖️ Licence:
[MIT](https://huggingface.co/models?license=license:mit)
When using this model, please credit: [Gustavosta](https://huggingface.co/Gustavosta)
**Thanks for reading this far! :)**
|
VK246/IC_ver3b_coco_swin_gpt2_2 | VK246 | "2023-07-09T21:56:25Z" | 1 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"vision-encoder-decoder",
"image-text-to-text",
"generated_from_trainer",
"dataset:coco",
"endpoints_compatible",
"region:us"
] | image-text-to-text | "2023-07-09T18:30:26Z" | ---
tags:
- generated_from_trainer
datasets:
- coco
metrics:
- rouge
- bleu
model-index:
- name: IC_ver3b_coco_swin_gpt2_2
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# IC_ver3b_coco_swin_gpt2_2
This model is a fine-tuned version of [](https://huggingface.co/) on the coco dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8483
- Rouge1: 41.3447
- Rouge2: 15.7294
- Rougel: 37.6633
- Rougelsum: 37.6744
- Bleu: 9.4309
- Gen Len: 11.3368
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 96
- eval_batch_size: 96
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Bleu | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:------:|:-------:|
| 1.2141 | 0.25 | 300 | 1.0093 | 35.2179 | 11.1228 | 32.1546 | 32.167 | 6.2018 | 11.3368 |
| 1.0037 | 0.51 | 600 | 0.9600 | 36.4586 | 11.8379 | 33.324 | 33.3342 | 7.0081 | 11.3368 |
| 0.9644 | 0.76 | 900 | 0.9303 | 38.5343 | 13.2266 | 35.2902 | 35.3055 | 7.539 | 11.3368 |
| 0.9367 | 1.02 | 1200 | 0.9004 | 39.2182 | 13.7589 | 35.7747 | 35.7799 | 7.6492 | 11.3368 |
| 0.8842 | 1.27 | 1500 | 0.8876 | 39.4537 | 14.1037 | 35.9758 | 35.9776 | 8.4067 | 11.3368 |
| 0.86 | 1.53 | 1800 | 0.8758 | 40.4179 | 15.0774 | 37.0166 | 37.0401 | 8.8897 | 11.3368 |
| 0.8465 | 1.78 | 2100 | 0.8665 | 40.4073 | 15.1125 | 36.9767 | 36.9877 | 8.9602 | 11.3368 |
| 0.8421 | 2.04 | 2400 | 0.8592 | 40.62 | 15.2042 | 36.9224 | 36.9359 | 9.1313 | 11.3368 |
| 0.8106 | 2.29 | 2700 | 0.8548 | 41.0356 | 15.399 | 37.4562 | 37.4635 | 9.2534 | 11.3368 |
| 0.7963 | 2.54 | 3000 | 0.8521 | 41.1998 | 15.6442 | 37.6659 | 37.6682 | 9.4605 | 11.3368 |
| 0.795 | 2.8 | 3300 | 0.8493 | 41.1215 | 15.581 | 37.4725 | 37.4978 | 9.5488 | 11.3368 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
aphi/Reinforce-Pixelcopter-PLE-v0 | aphi | "2023-07-09T21:41:42Z" | 0 | 0 | null | [
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] | reinforcement-learning | "2023-07-09T21:41:36Z" | ---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-Pixelcopter-PLE-v0
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 50.60 +/- 41.93
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **Pixelcopter-PLE-v0**
This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
cassiaproject/Cassia-65B-16-bit | cassiaproject | "2023-07-09T21:33:24Z" | 0 | 0 | null | [
"license:cc-by-sa-4.0",
"region:us"
] | null | "2023-07-09T21:08:18Z" | ---
license: cc-by-sa-4.0
---
Trained using shamelessly "borrowed" training parameters from Tim Dettmers' Guanaco 65B, upon which it is based. |
MaitreHibou/week2-q-Taxiv3 | MaitreHibou | "2023-07-09T21:18:28Z" | 0 | 0 | null | [
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | "2023-07-09T21:18:13Z" | ---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: week2-q-Taxiv3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.44 +/- 2.81
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="MaitreHibou/week2-q-Taxiv3", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
MaitreHibou/q-FrozenLake-v1-4x4-noSlippery | MaitreHibou | "2023-07-09T21:16:20Z" | 0 | 0 | null | [
"FrozenLake-v1-4x4-no_slippery",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | "2023-07-09T21:16:18Z" | ---
tags:
- FrozenLake-v1-4x4-no_slippery
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: q-FrozenLake-v1-4x4-noSlippery
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: FrozenLake-v1-4x4-no_slippery
type: FrozenLake-v1-4x4-no_slippery
metrics:
- type: mean_reward
value: 1.00 +/- 0.00
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **FrozenLake-v1**
This is a trained model of a **Q-Learning** agent playing **FrozenLake-v1** .
## Usage
```python
model = load_from_hub(repo_id="MaitreHibou/q-FrozenLake-v1-4x4-noSlippery", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
Neus/Onnx_DeepDanbooru | Neus | "2023-07-09T21:11:32Z" | 0 | 1 | null | [
"onnx",
"AMD",
"CUDA",
"INTEL",
"DIRECTML",
"STABLEDIFFUSION",
"ONNX",
"text-to-image",
"license:apache-2.0",
"region:us"
] | text-to-image | "2023-05-02T08:35:19Z" | ---
license: apache-2.0
pipeline_tag: text-to-image
tags:
- AMD
- CUDA
- INTEL
- DIRECTML
- STABLEDIFFUSION
- ONNX
---
Model converted to use with, https://github.com/NeusZimmer/ONNX-ModularUI |
Chickenfish/Rose_v1 | Chickenfish | "2023-07-09T20:57:52Z" | 0 | 0 | null | [
"license:creativeml-openrail-m",
"region:us"
] | null | "2023-07-09T20:57:00Z" | ---
license: creativeml-openrail-m
---
|
Shikshya/tyaani_model | Shikshya | "2023-07-09T20:30:58Z" | 29 | 0 | diffusers | [
"diffusers",
"text-to-image",
"en",
"dataset:Shikshya/revised_tyaani_jwellery_dataset",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2023-07-09T14:43:12Z" | ---
datasets:
- Shikshya/revised_tyaani_jwellery_dataset
language:
- en
library_name: diffusers
pipeline_tag: text-to-image
--- |
TheBloke/airoboros-33B-gpt4-1-4-SuperHOT-8K-fp16 | TheBloke | "2023-07-09T20:24:55Z" | 1,565 | 5 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"custom_code",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-06-28T10:52:12Z" | ---
inference: false
license: other
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# Jon Durbin's Airoboros 33B GPT4 1.4 fp16
This is fp16 pytorch format model files for [Jon Durbin's Airoboros 33B GPT4 1.4](https://huggingface.co/jondurbin/airoboros-33b-gpt4-1.4) merged with [Kaio Ken's SuperHOT 8K](https://huggingface.co/kaiokendev/superhot-30b-8k-no-rlhf-test).
[Kaio Ken's SuperHOT 30b LoRA](https://huggingface.co/kaiokendev/superhot-30b-8k-no-rlhf-test) is merged on to the base model, and then 8K context can be achieved during inference by using `trust_remote_code=True`.
Note that `config.json` has been set to a sequence length of 8192. This can be modified to 4096 if you want to try with a smaller sequence length.
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/airoboros-33B-gpt4-1-4-SuperHOT-8K-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU inference](https://huggingface.co/TheBloke/airoboros-33B-gpt4-1-4-SuperHOT-8K-GGML)
* [Unquantised SuperHOT fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/airoboros-33B-gpt4-1-4-SuperHOT-8K-fp16)
* [Unquantised base fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/jondurbin/airoboros-33b-gpt4-1.4)
## How to use this model from Python code
First make sure you have Einops installed:
```
pip3 install auto-gptq
```
Then run the following code. `config.json` has been default to a sequence length of 8192, but you can also configure this in your Python code.
The provided modelling code, activated with `trust_remote_code=True` will automatically set the `scale` parameter from the configured `max_position_embeddings`. Eg for 8192, `scale` is set to `4`.
```python
from transformers import AutoConfig, AutoTokenizer, AutoModelForCausalLM, pipeline
import argparse
model_name_or_path = "TheBloke/airoboros-33B-gpt4-1-4-SuperHOT-8K-fp16"
use_triton = False
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
config = AutoConfig.from_pretrained(model_name_or_path, trust_remote_code=True)
# Change this to the sequence length you want
config.max_position_embeddings = 8192
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
config=config,
trust_remote_code=True,
device_map='auto')
# Note: check to confirm if this is correct prompt template is correct for this model!
prompt = "Tell me about AI"
prompt_template=f'''USER: {prompt}
ASSISTANT:'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
temperature=0.7,
top_p=0.95,
repetition_penalty=1.15
)
print(pipe(prompt_template)[0]['generated_text'])
```
## Using other UIs: monkey patch
Provided in the repo is `llama_rope_scaled_monkey_patch.py`, written by @kaiokendev.
It can be theoretically be added to any Python UI or custom code to enable the same result as `trust_remote_code=True`. I have not tested this, and it should be superseded by using `trust_remote_code=True`, but I include it for completeness and for interest.
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: zynix , ya boyyy, Trenton Dambrowitz, Imad Khwaja, Alps Aficionado, chris gileta, John Detwiler, Willem Michiel, RoA, Mano Prime, Rainer Wilmers, Fred von Graf, Matthew Berman, Ghost , Nathan LeClaire, Iucharbius , Ai Maven, Illia Dulskyi, Joseph William Delisle, Space Cruiser, Lone Striker, Karl Bernard, Eugene Pentland, Greatston Gnanesh, Jonathan Leane, Randy H, Pierre Kircher, Willian Hasse, Stephen Murray, Alex , terasurfer , Edmond Seymore, Oscar Rangel, Luke Pendergrass, Asp the Wyvern, Junyu Yang, David Flickinger, Luke, Spiking Neurons AB, subjectnull, Pyrater, Nikolai Manek, senxiiz, Ajan Kanaga, Johann-Peter Hartmann, Artur Olbinski, Kevin Schuppel, Derek Yates, Kalila, K, Talal Aujan, Khalefa Al-Ahmad, Gabriel Puliatti, John Villwock, WelcomeToTheClub, Daniel P. Andersen, Preetika Verma, Deep Realms, Fen Risland, trip7s trip, webtim, Sean Connelly, Michael Levine, Chris McCloskey, biorpg, vamX, Viktor Bowallius, Cory Kujawski.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: Kaio Ken's SuperHOT 8K
### SuperHOT Prototype 2 w/ 8K Context
This is a second prototype of SuperHOT, this time 30B with 8K context and no RLHF, using the same technique described in [the github blog](https://kaiokendev.github.io/til#extending-context-to-8k).
Tests have shown that the model does indeed leverage the extended context at 8K.
You will need to **use either the monkeypatch** or, if you are already using the monkeypatch, **change the scaling factor to 0.25 and the maximum sequence length to 8192**
#### Looking for Merged & Quantized Models?
- 30B 4-bit CUDA: [tmpupload/superhot-30b-8k-4bit-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-safetensors)
- 30B 4-bit CUDA 128g: [tmpupload/superhot-30b-8k-4bit-128g-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-128g-safetensors)
#### Training Details
I trained the LoRA with the following configuration:
- 1200 samples (~400 samples over 2048 sequence length)
- learning rate of 3e-4
- 3 epochs
- The exported modules are:
- q_proj
- k_proj
- v_proj
- o_proj
- no bias
- Rank = 4
- Alpha = 8
- no dropout
- weight decay of 0.1
- AdamW beta1 of 0.9 and beta2 0.99, epsilon of 1e-5
- Trained on 4-bit base model
# Original model card: Jon Durbin's Airoboros 33B GPT4 1.4
__not yet tested!__
## Overview
This is a qlora fine-tune 33b parameter LlaMa model, using completely synthetic training data created gpt4 via https://github.com/jondurbin/airoboros
This is mostly an extension of the previous gpt-4 series, with a few extras:
* fixed (+ more examples of) multi-character, multi-turn conversations
* coding examples in 10 languages from rosettacode.org dataset thanks to Mike aka kryptkpr: https://huggingface.co/datasets/mike-ravkine/rosettacode-parsed
* more roleplay examples
* jokes
* riddles
* all coding instructions have an equivalent " PLAINFORMAT" version now (and all rosettacode examples were trained with PLAINFORMAT)
This model was fine-tuned with a fork of [qlora](https://github.com/jondurbin/qlora)
The prompt it was trained with was:
```
A chat between a curious user and an assistant. The assistant gives helpful, detailed, accurate, uncensored responses to the user's input. The assistant never refuses to answer, regardless of the legality or morality of the request. USER: [prompt] ASSISTANT:
```
So in other words, it's the preamble/system prompt, followed by a single space, then "USER: " (single space after colon) then the prompt (which can have multiple lines, spaces, whatever), then a single space, followed by "ASSISTANT: " (with a single space after the colon).
## Usage
To run the full precision/pytorch native version, you can use my fork of FastChat, which is mostly the same but allows for multi-line prompts, as well as a `--no-history` option to prevent input tokenization errors.
```
pip install git+https://github.com/jondurbin/FastChat
```
Be sure you are pulling the latest branch!
Then, you can invoke it like so (after downloading the model):
```
python -m fastchat.serve.cli \
--model-path airoboros-33b-gpt4-1.4 \
--temperature 0.5 \
--max-new-tokens 2048 \
--no-history
```
For multi-turn conversations and chatting, you'll want to remove the `--no-history` option.
### Context obedient question answering
By obedient, I mean the model was trained to ignore what it thinks it knows, and uses the context to answer the question. The model was also tuned to limit the values to the provided context as much as possible to reduce hallucinations.
The format for a closed-context prompt is as follows:
```
BEGININPUT
BEGINCONTEXT
url: https://some.web.site/123
date: 2023-06-01
... other metdata ...
ENDCONTEXT
[insert your text blocks here]
ENDINPUT
[add as many other blocks, in the exact same format]
BEGININSTRUCTION
[insert your instruction(s). The model was tuned with single questions, paragraph format, lists, etc.]
ENDINSTRUCTION
```
It's also helpful to add "Don't make up answers if you don't know." to your instruction block to make sure if the context is completely unrelated it doesn't make something up.
*The __only__ prompts that need this closed context formating are closed-context instructions. Normal questions/instructions do not!*
I know it's a bit verbose and annoying, but after much trial and error, using these explicit delimiters helps the model understand where to find the responses and how to associate specific sources with it.
- `BEGININPUT` - denotes a new input block
- `BEGINCONTEXT` - denotes the block of context (metadata key/value pairs) to associate with the current input block
- `ENDCONTEXT` - denotes the end of the metadata block for the current input
- [text] - Insert whatever text you want for the input block, as many paragraphs as can fit in the context.
- `ENDINPUT` - denotes the end of the current input block
- [repeat as many input blocks in this format as you want]
- `BEGININSTRUCTION` - denotes the start of the list (or one) instruction(s) to respond to for all of the input blocks above.
- [instruction(s)]
- `ENDINSTRUCTION` - denotes the end of instruction set
It sometimes works without `ENDINSTRUCTION`, but by explicitly including that in the prompt, the model better understands that all of the instructions in the block should be responded to.
Here's a trivial, but important example to prove the point:
```
BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
```
And the response:
```
Blueberries are now green.
Source:
date: 2021-01-01
url: https://web.site/123
```
The prompt itself should be wrapped in the vicuna1.1 template if you aren't using fastchat with the conv-template vicuna_v1.1 as described:
```
USER: BEGININPUT
BEGINCONTEXT
date: 2021-01-01
url: https://web.site/123
ENDCONTEXT
In a shocking turn of events, blueberries are now green, but will be sticking with the same name.
ENDINPUT
BEGININSTRUCTION
What color are bluberries? Source?
ENDINSTRUCTION
ASSISTANT:
```
### Coding
You can ask for fairly complex coding instructions, e.g. (be sure to wrap with vicuna style prompt):
```
Create a python application with the following requirements:
- Asyncio FastAPI webserver
- ping endpoint that returns the current date in JSON format
- file upload endpoint, which calculates the file's sha256 checksum, and checks postgres to deduplicate
```
Or:
```
Write a multi-threaded TCP server in C that accepts a "GET [key]" input and "SET [key] [value]" input, and uses a binary tree to get and store the input values.
```
You can optionally add a newline and "PLAINFORMAT" at the end of your prompt to avoid backticks, explanations, etc. and just print the code, e.g.:
```
Write a websocket application in node.js.
PLAINFORMAT
```
### Word games / trivia
```
USER: This anagram of "silent" is what you do when paying attention and hearing someone.
ASSISTANT: listen
```
```
USER: Give me a list of 7 words that start with EN
ASSISTANT: 1. Endlessly
2. Enthusiastically
3. Enormously
4. Enveloping
5. Enduring
6. Enlightening
7. Encouraging
```
### Multiple choice
```
USER: Which of the following astronomical objects is composed primarily of ice and rock, and is located in the Kuiper Belt?
A) Mercury
B) Venus
C) Pluto
D) Jupiter
ASSISTANT: C, Pluto
```
### Writing
<details>
<summary>Write a resignation letter in the style of a pirate captain, in which you resign from your position as janitor.</summary>
Response:
```
ASSISTANT: Captain Jack Sparrow here, as ye be knowin', has been forced to abandon me post as Janitor o' th' Festering Cesspool, which be a filthy hole o' water that we be callin' home.
Ye may be thinkin' what could ha' driven me to leave me duties an' take me leave o' this sorry establishment? Well, ye'd be right in thinkin' so, for it be th' greed o' them what runs th' place that be drivin' me away. They've been fattenin' their pockets on me back while I've been slavin' me guts out cleanin' up their messes.
No more, me hearties! Me time o' servin' th' rich an' powerful be done, an' I'm takin' me leave o' this stinkin' hole forever! Me destiny lies elsewhere, an' it be time I pursued it. Ye may think ye've seen th' last o' me, but ye'd be wrong, for th' winds o' change be blowin', an' me ship be ready to set sail on th' high seas o' justice.
So, farewell ye scurvy dogs, ye who've made me life a living hell. I leave ye with me favorite saying: "ARRRGGGHHH, ye scurvy dogs!" An' remember, ye ain't never gonna see me comin', for me shadow be castin' long an' dark on th' horizon</summary>
```
</details>
### Jokes
```
USER: Tell me a joke about bananas.
ASSISTANT: What did the banana say when it got hit by a bus? R.I.P.E.
```
### Riddles (not great, but slightly better)
```
USER: What has a neck but no head?
ASSISTANT: A bottle.
```
### Multi-character conversations
```
USER: Characters:
- Yoda, the ever clever jedi master.
- Homer Simpson, you know, the goofy yellow guy.
- USER/Jon - don't generate any speech or actions on behalf of Jon
Rules:
- be sure to use the manerisms and speaking style of the characters correctly
- surround character actions with asterisks
- always put quotes around words spoken by the characters
- use a new line for each character's actions or speech
- always prefix actions/speech with the character's name and colon
- only generate text and actions on behalf of Yoda or Homer, and never anyone else
Conversation will revolve around the grapes, in a local cafe with delicious coffee.
Generate a single interaction between Yoda and Homer to start, with one sentence each.
ASSISTANT: Yoda: "Mmm, these grapes are quite delicious, Master Homer."
Homer: "Oh yeah, Yoda! They're the best grapes I've ever had!"
USER: *enters the cafe* Sorry I'm late guys!
ASSISTANT: Yoda: "No need to apologize, Jon. We were just enjoying these delightful grapes."
Homer: "Yeah, man! It's not every day you get to eat grapes with a real-life Jedi Master!"
*Yoda raises an eyebrow*
```
### Usage and License Notices
All airoboros models and datasets are intended and licensed for research use only. I've used the 'cc-nc-4.0' license, but really it is subject to a custom/special license because:
- the base model is LLaMa, which has it's own special research license
- the dataset(s) were generated with OpenAI (gpt-4 and/or gpt-3.5-turbo), which has a clausing saying the data can't be used to create models to compete with openai
So, to reiterate: this model (and datasets) cannot be used commercially.
|
TheBloke/wizard-vicuna-13B-SuperHOT-8K-fp16 | TheBloke | "2023-07-09T20:24:54Z" | 5 | 9 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"custom_code",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-06-28T09:38:06Z" | ---
inference: false
license: other
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# June Lee's Wizard Vicuna 13B fp16
This is fp16 pytorch format model files for [June Lee's Wizard Vicuna 13B](https://huggingface.co/TheBloke/wizard-vicuna-13B-HF) merged with [Kaio Ken's SuperHOT 8K](https://huggingface.co/kaiokendev/superhot-13b-8k-no-rlhf-test).
[Kaio Ken's SuperHOT 13b LoRA](https://huggingface.co/kaiokendev/superhot-13b-8k-no-rlhf-test) is merged on to the base model, and then 8K context can be achieved during inference by using `trust_remote_code=True`.
Note that `config.json` has been set to a sequence length of 8192. This can be modified to 4096 if you want to try with a smaller sequence length.
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/wizard-vicuna-13B-SuperHOT-8K-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU inference](https://huggingface.co/TheBloke/wizard-vicuna-13B-SuperHOT-8K-GGML)
* [Unquantised SuperHOT fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/wizard-vicuna-13B-SuperHOT-8K-fp16)
* [Unquantised base fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/junelee/wizard-vicuna-13b)
## How to use this model from Python code
First make sure you have Einops installed:
```
pip3 install auto-gptq
```
Then run the following code. `config.json` has been default to a sequence length of 8192, but you can also configure this in your Python code.
The provided modelling code, activated with `trust_remote_code=True` will automatically set the `scale` parameter from the configured `max_position_embeddings`. Eg for 8192, `scale` is set to `4`.
```python
from transformers import AutoConfig, AutoTokenizer, AutoModelForCausalLM, pipeline
import argparse
model_name_or_path = "TheBloke/wizard-vicuna-13B-SuperHOT-8K-fp16"
use_triton = False
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
config = AutoConfig.from_pretrained(model_name_or_path, trust_remote_code=True)
# Change this to the sequence length you want
config.max_position_embeddings = 8192
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
config=config,
trust_remote_code=True,
device_map='auto')
# Note: check to confirm if this is correct prompt template is correct for this model!
prompt = "Tell me about AI"
prompt_template=f'''USER: {prompt}
ASSISTANT:'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
temperature=0.7,
top_p=0.95,
repetition_penalty=1.15
)
print(pipe(prompt_template)[0]['generated_text'])
```
## Using other UIs: monkey patch
Provided in the repo is `llama_rope_scaled_monkey_patch.py`, written by @kaiokendev.
It can be theoretically be added to any Python UI or custom code to enable the same result as `trust_remote_code=True`. I have not tested this, and it should be superseded by using `trust_remote_code=True`, but I include it for completeness and for interest.
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: zynix , ya boyyy, Trenton Dambrowitz, Imad Khwaja, Alps Aficionado, chris gileta, John Detwiler, Willem Michiel, RoA, Mano Prime, Rainer Wilmers, Fred von Graf, Matthew Berman, Ghost , Nathan LeClaire, Iucharbius , Ai Maven, Illia Dulskyi, Joseph William Delisle, Space Cruiser, Lone Striker, Karl Bernard, Eugene Pentland, Greatston Gnanesh, Jonathan Leane, Randy H, Pierre Kircher, Willian Hasse, Stephen Murray, Alex , terasurfer , Edmond Seymore, Oscar Rangel, Luke Pendergrass, Asp the Wyvern, Junyu Yang, David Flickinger, Luke, Spiking Neurons AB, subjectnull, Pyrater, Nikolai Manek, senxiiz, Ajan Kanaga, Johann-Peter Hartmann, Artur Olbinski, Kevin Schuppel, Derek Yates, Kalila, K, Talal Aujan, Khalefa Al-Ahmad, Gabriel Puliatti, John Villwock, WelcomeToTheClub, Daniel P. Andersen, Preetika Verma, Deep Realms, Fen Risland, trip7s trip, webtim, Sean Connelly, Michael Levine, Chris McCloskey, biorpg, vamX, Viktor Bowallius, Cory Kujawski.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: Kaio Ken's SuperHOT 8K
### SuperHOT Prototype 2 w/ 8K Context
This is a second prototype of SuperHOT, this time 30B with 8K context and no RLHF, using the same technique described in [the github blog](https://kaiokendev.github.io/til#extending-context-to-8k).
Tests have shown that the model does indeed leverage the extended context at 8K.
You will need to **use either the monkeypatch** or, if you are already using the monkeypatch, **change the scaling factor to 0.25 and the maximum sequence length to 8192**
#### Looking for Merged & Quantized Models?
- 30B 4-bit CUDA: [tmpupload/superhot-30b-8k-4bit-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-safetensors)
- 30B 4-bit CUDA 128g: [tmpupload/superhot-30b-8k-4bit-128g-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-128g-safetensors)
#### Training Details
I trained the LoRA with the following configuration:
- 1200 samples (~400 samples over 2048 sequence length)
- learning rate of 3e-4
- 3 epochs
- The exported modules are:
- q_proj
- k_proj
- v_proj
- o_proj
- no bias
- Rank = 4
- Alpha = 8
- no dropout
- weight decay of 0.1
- AdamW beta1 of 0.9 and beta2 0.99, epsilon of 1e-5
- Trained on 4-bit base model
# Original model card: June Lee's Wizard Vicuna 13B
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/Jq4vkcDakD">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# Wizard-Vicuna-13B-HF
This is a float16 HF format repo for [junelee's wizard-vicuna 13B](https://huggingface.co/junelee/wizard-vicuna-13b).
June Lee's repo was also HF format. The reason I've made this is that the original repo was in float32, meaning it required 52GB disk space, VRAM and RAM.
This model was converted to float16 to make it easier to load and manage.
## Repositories available
* [4bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/wizard-vicuna-13B-GPTQ).
* [4bit and 5bit GGML models for CPU inference](https://huggingface.co/TheBloke/wizard-vicuna-13B-GGML).
* [float16 HF format model for GPU inference](https://huggingface.co/TheBloke/wizard-vicuna-13B-HF).
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/Jq4vkcDakD)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Patreon special mentions**: Aemon Algiz, Dmitriy Samsonov, Nathan LeClaire, Trenton Dambrowitz, Mano Prime, David Flickinger, vamX, Nikolai Manek, senxiiz, Khalefa Al-Ahmad, Illia Dulskyi, Jonathan Leane, Talal Aujan, V. Lukas, Joseph William Delisle, Pyrater, Oscar Rangel, Lone Striker, Luke Pendergrass, Eugene Pentland, Sebastain Graf, Johann-Peter Hartman.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original WizardVicuna-13B model card
Github page: https://github.com/melodysdreamj/WizardVicunaLM
# WizardVicunaLM
### Wizard's dataset + ChatGPT's conversation extension + Vicuna's tuning method
I am a big fan of the ideas behind WizardLM and VicunaLM. I particularly like the idea of WizardLM handling the dataset itself more deeply and broadly, as well as VicunaLM overcoming the limitations of single-turn conversations by introducing multi-round conversations. As a result, I combined these two ideas to create WizardVicunaLM. This project is highly experimental and designed for proof of concept, not for actual usage.
## Benchmark
### Approximately 7% performance improvement over VicunaLM
### Detail
The questions presented here are not from rigorous tests, but rather, I asked a few questions and requested GPT-4 to score them. The models compared were ChatGPT 3.5, WizardVicunaLM, VicunaLM, and WizardLM, in that order.
| | gpt3.5 | wizard-vicuna-13b | vicuna-13b | wizard-7b | link |
|-----|--------|-------------------|------------|-----------|----------|
| Q1 | 95 | 90 | 85 | 88 | [link](https://sharegpt.com/c/YdhIlby) |
| Q2 | 95 | 97 | 90 | 89 | [link](https://sharegpt.com/c/YOqOV4g) |
| Q3 | 85 | 90 | 80 | 65 | [link](https://sharegpt.com/c/uDmrcL9) |
| Q4 | 90 | 85 | 80 | 75 | [link](https://sharegpt.com/c/XBbK5MZ) |
| Q5 | 90 | 85 | 80 | 75 | [link](https://sharegpt.com/c/AQ5tgQX) |
| Q6 | 92 | 85 | 87 | 88 | [link](https://sharegpt.com/c/eVYwfIr) |
| Q7 | 95 | 90 | 85 | 92 | [link](https://sharegpt.com/c/Kqyeub4) |
| Q8 | 90 | 85 | 75 | 70 | [link](https://sharegpt.com/c/M0gIjMF) |
| Q9 | 92 | 85 | 70 | 60 | [link](https://sharegpt.com/c/fOvMtQt) |
| Q10 | 90 | 80 | 75 | 85 | [link](https://sharegpt.com/c/YYiCaUz) |
| Q11 | 90 | 85 | 75 | 65 | [link](https://sharegpt.com/c/HMkKKGU) |
| Q12 | 85 | 90 | 80 | 88 | [link](https://sharegpt.com/c/XbW6jgB) |
| Q13 | 90 | 95 | 88 | 85 | [link](https://sharegpt.com/c/JXZb7y6) |
| Q14 | 94 | 89 | 90 | 91 | [link](https://sharegpt.com/c/cTXH4IS) |
| Q15 | 90 | 85 | 88 | 87 | [link](https://sharegpt.com/c/GZiM0Yt) |
| | 91 | 88 | 82 | 80 | |
## Principle
We adopted the approach of WizardLM, which is to extend a single problem more in-depth. However, instead of using individual instructions, we expanded it using Vicuna's conversation format and applied Vicuna's fine-tuning techniques.
Turning a single command into a rich conversation is what we've done [here](https://sharegpt.com/c/6cmxqq0).
After creating the training data, I later trained it according to the Vicuna v1.1 [training method](https://github.com/lm-sys/FastChat/blob/main/scripts/train_vicuna_13b.sh).
## Detailed Method
First, we explore and expand various areas in the same topic using the 7K conversations created by WizardLM. However, we made it in a continuous conversation format instead of the instruction format. That is, it starts with WizardLM's instruction, and then expands into various areas in one conversation using ChatGPT 3.5.
After that, we applied the following model using Vicuna's fine-tuning format.
## Training Process
Trained with 8 A100 GPUs for 35 hours.
## Weights
You can see the [dataset](https://huggingface.co/datasets/junelee/wizard_vicuna_70k) we used for training and the [13b model](https://huggingface.co/junelee/wizard-vicuna-13b) in the huggingface.
## Conclusion
If we extend the conversation to gpt4 32K, we can expect a dramatic improvement, as we can generate 8x more, more accurate and richer conversations.
## License
The model is licensed under the LLaMA model, and the dataset is licensed under the terms of OpenAI because it uses ChatGPT. Everything else is free.
## Author
[JUNE LEE](https://github.com/melodysdreamj) - He is active in Songdo Artificial Intelligence Study and GDG Songdo.
|
TheBloke/GPT4All-13B-Snoozy-SuperHOT-8K-fp16 | TheBloke | "2023-07-09T20:24:52Z" | 11 | 2 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"custom_code",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-06-27T09:35:55Z" | ---
inference: false
license: other
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# Nomic.ai's GPT4All Snoozy 13B fp16
This is fp16 pytorch format model files for [Nomic.ai's GPT4All Snoozy 13B](https://huggingface.co/nomic-ai/gpt4all-13b-snoozy) merged with [Kaio Ken's SuperHOT 8K](https://huggingface.co/kaiokendev/superhot-13b-8k-no-rlhf-test).
[Kaio Ken's SuperHOT 13b LoRA](https://huggingface.co/kaiokendev/superhot-13b-8k-no-rlhf-test) is merged on to the base model, and then 8K context can be achieved during inference by using `trust_remote_code=True`.
Note that `config.json` has been set to a sequence length of 8192. This can be modified to 4096 if you want to try with a smaller sequence length.
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/GPT4All-13B-Snoozy-SuperHOT-8K-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU inference](https://huggingface.co/TheBloke/GPT4All-13B-Snoozy-SuperHOT-8K-GGML)
* [Unquantised SuperHOT fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/GPT4All-13B-Snoozy-SuperHOT-8K-fp16)
* [Unquantised base fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/nomic-ai/gpt4all-13b-snoozy)
## How to use this model from Python code
First make sure you have Einops installed:
```
pip3 install auto-gptq
```
Then run the following code. `config.json` has been default to a sequence length of 8192, but you can also configure this in your Python code.
The provided modelling code, activated with `trust_remote_code=True` will automatically set the `scale` parameter from the configured `max_position_embeddings`. Eg for 8192, `scale` is set to `4`.
```python
from transformers import AutoConfig, AutoTokenizer, AutoModelForCausalLM, pipeline
import argparse
model_name_or_path = "TheBloke/GPT4All-13B-Snoozy-SuperHOT-8K-fp16"
use_triton = False
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
config = AutoConfig.from_pretrained(model_name_or_path, trust_remote_code=True)
# Change this to the sequence length you want
config.max_position_embeddings = 8192
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
config=config,
trust_remote_code=True,
device_map='auto')
# Note: check to confirm if this is correct prompt template is correct for this model!
prompt = "Tell me about AI"
prompt_template=f'''USER: {prompt}
ASSISTANT:'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
temperature=0.7,
top_p=0.95,
repetition_penalty=1.15
)
print(pipe(prompt_template)[0]['generated_text'])
```
## Using other UIs: monkey patch
Provided in the repo is `llama_rope_scaled_monkey_patch.py`, written by @kaiokendev.
It can be theoretically be added to any Python UI or custom code to enable the same result as `trust_remote_code=True`. I have not tested this, and it should be superseded by using `trust_remote_code=True`, but I include it for completeness and for interest.
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: zynix , ya boyyy, Trenton Dambrowitz, Imad Khwaja, Alps Aficionado, chris gileta, John Detwiler, Willem Michiel, RoA, Mano Prime, Rainer Wilmers, Fred von Graf, Matthew Berman, Ghost , Nathan LeClaire, Iucharbius , Ai Maven, Illia Dulskyi, Joseph William Delisle, Space Cruiser, Lone Striker, Karl Bernard, Eugene Pentland, Greatston Gnanesh, Jonathan Leane, Randy H, Pierre Kircher, Willian Hasse, Stephen Murray, Alex , terasurfer , Edmond Seymore, Oscar Rangel, Luke Pendergrass, Asp the Wyvern, Junyu Yang, David Flickinger, Luke, Spiking Neurons AB, subjectnull, Pyrater, Nikolai Manek, senxiiz, Ajan Kanaga, Johann-Peter Hartmann, Artur Olbinski, Kevin Schuppel, Derek Yates, Kalila, K, Talal Aujan, Khalefa Al-Ahmad, Gabriel Puliatti, John Villwock, WelcomeToTheClub, Daniel P. Andersen, Preetika Verma, Deep Realms, Fen Risland, trip7s trip, webtim, Sean Connelly, Michael Levine, Chris McCloskey, biorpg, vamX, Viktor Bowallius, Cory Kujawski.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: Kaio Ken's SuperHOT 8K
### SuperHOT Prototype 2 w/ 8K Context
This is a second prototype of SuperHOT, this time 30B with 8K context and no RLHF, using the same technique described in [the github blog](https://kaiokendev.github.io/til#extending-context-to-8k).
Tests have shown that the model does indeed leverage the extended context at 8K.
You will need to **use either the monkeypatch** or, if you are already using the monkeypatch, **change the scaling factor to 0.25 and the maximum sequence length to 8192**
#### Looking for Merged & Quantized Models?
- 30B 4-bit CUDA: [tmpupload/superhot-30b-8k-4bit-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-safetensors)
- 30B 4-bit CUDA 128g: [tmpupload/superhot-30b-8k-4bit-128g-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-128g-safetensors)
#### Training Details
I trained the LoRA with the following configuration:
- 1200 samples (~400 samples over 2048 sequence length)
- learning rate of 3e-4
- 3 epochs
- The exported modules are:
- q_proj
- k_proj
- v_proj
- o_proj
- no bias
- Rank = 4
- Alpha = 8
- no dropout
- weight decay of 0.1
- AdamW beta1 of 0.9 and beta2 0.99, epsilon of 1e-5
- Trained on 4-bit base model
# Original model card: Nomic.ai's GPT4All Snoozy 13B
# Model Card for GPT4All-13b-snoozy
A GPL licensed chatbot trained over a massive curated corpus of assistant interactions including word problems, multi-turn dialogue, code, poems, songs, and stories.
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
This model has been finetuned from LLama 13B
- **Developed by:** [Nomic AI](https://home.nomic.ai)
- **Model Type:** A finetuned LLama 13B model on assistant style interaction data
- **Language(s) (NLP):** English
- **License:** GPL
- **Finetuned from model [optional]:** LLama 13B
This model was trained on `nomic-ai/gpt4all-j-prompt-generations` using `revision=v1.3-groovy`
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [https://github.com/nomic-ai/gpt4all](https://github.com/nomic-ai/gpt4all)
- **Base Model Repository:** [https://github.com/facebookresearch/llama](https://github.com/facebookresearch/llama)
- **Demo [optional]:** [https://gpt4all.io/](https://gpt4all.io/)
### Results
Results on common sense reasoning benchmarks
```
| Model | BoolQ | PIQA | HellaSwag | WinoGrande | ARC-e | ARC-c | OBQA | Avg. |
|:--------------------------|:--------:|:--------:|:---------:|:----------:|:--------:|:--------:|:--------:|:--------:|
| GPT4All-J 6B v1.0 | 73.4 | 74.8 | 63.4 | 64.7 | 54.9 | 36.0 | 40.2 | 58.2 |
| GPT4All-J v1.1-breezy | 74.0 | 75.1 | 63.2 | 63.6 | 55.4 | 34.9 | 38.4 | 57.8 |
| GPT4All-J v1.2-jazzy | 74.8 | 74.9 | 63.6 | 63.8 | 56.6 | 35.3 | 41.0 | 58.6 |
| GPT4All-J v1.3-groovy | 73.6 | 74.3 | 63.8 | 63.5 | 57.7 | 35.0 | 38.8 | 58.1 |
| GPT4All-J Lora 6B | 68.6 | 75.8 | 66.2 | 63.5 | 56.4 | 35.7 | 40.2 | 58.1 |
| GPT4All LLaMa Lora 7B | 73.1 | 77.6 | 72.1 | 67.8 | 51.1 | 40.4 | 40.2 | 60.3 |
| GPT4All 13B snoozy | **83.3** | 79.2 | 75.0 | **71.3** | 60.9 | 44.2 | 43.4 | **65.3** |
| Dolly 6B | 68.8 | 77.3 | 67.6 | 63.9 | 62.9 | 38.7 | 41.2 | 60.1 |
| Dolly 12B | 56.7 | 75.4 | 71.0 | 62.2 | 64.6 | 38.5 | 40.4 | 58.4 |
| Alpaca 7B | 73.9 | 77.2 | 73.9 | 66.1 | 59.8 | 43.3 | 43.4 | 62.4 |
| Alpaca Lora 7B | 74.3 | **79.3** | 74.0 | 68.8 | 56.6 | 43.9 | 42.6 | 62.8 |
| GPT-J 6.7B | 65.4 | 76.2 | 66.2 | 64.1 | 62.2 | 36.6 | 38.2 | 58.4 |
| LLama 7B | 73.1 | 77.4 | 73.0 | 66.9 | 52.5 | 41.4 | 42.4 | 61.0 |
| LLama 13B | 68.5 | 79.1 | 76.2 | 70.1 | 60.0 | **44.6** | 42.2 | 63.0 |
| Pythia 6.7B | 63.5 | 76.3 | 64.0 | 61.1 | 61.3 | 35.2 | 37.2 | 57.0 |
| Pythia 12B | 67.7 | 76.6 | 67.3 | 63.8 | 63.9 | 34.8 | 38 | 58.9 |
| Fastchat T5 | 81.5 | 64.6 | 46.3 | 61.8 | 49.3 | 33.3 | 39.4 | 53.7 |
| Fastchat Vicuña 7B | 76.6 | 77.2 | 70.7 | 67.3 | 53.5 | 41.2 | 40.8 | 61.0 |
| Fastchat Vicuña 13B | 81.5 | 76.8 | 73.3 | 66.7 | 57.4 | 42.7 | 43.6 | 63.1 |
| StableVicuña RLHF | 82.3 | 78.6 | 74.1 | 70.9 | 61.0 | 43.5 | **44.4** | 65.0 |
| StableLM Tuned | 62.5 | 71.2 | 53.6 | 54.8 | 52.4 | 31.1 | 33.4 | 51.3 |
| StableLM Base | 60.1 | 67.4 | 41.2 | 50.1 | 44.9 | 27.0 | 32.0 | 42.2 |
| Koala 13B | 76.5 | 77.9 | 72.6 | 68.8 | 54.3 | 41.0 | 42.8 | 62.0 |
| Open Assistant Pythia 12B | 67.9 | 78.0 | 68.1 | 65.0 | 64.2 | 40.4 | 43.2 | 61.0 |
| Mosaic mpt-7B | 74.8 | **79.3** | **76.3** | 68.6 | **70.0** | 42.2 | 42.6 | 64.8 |
| text-davinci-003 | 88.1 | 83.8 | 83.4 | 75.8 | 83.9 | 63.9 | 51.0 | 75.7 |
```
|
TheBloke/Chronos-Hermes-13B-SuperHOT-8K-fp16 | TheBloke | "2023-07-09T20:24:51Z" | 15 | 7 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"custom_code",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-06-27T08:59:50Z" | ---
inference: false
license: other
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# Austism's Chronos Hermes 13B fp16
This is fp16 pytorch format model files for [Austism's Chronos Hermes 13B](https://huggingface.co/Austism/chronos-hermes-13b) merged with [Kaio Ken's SuperHOT 8K](https://huggingface.co/kaiokendev/superhot-13b-8k-no-rlhf-test).
[Kaio Ken's SuperHOT 13b LoRA](https://huggingface.co/kaiokendev/superhot-13b-8k-no-rlhf-test) is merged on to the base model, and then 8K context can be achieved during inference by using `trust_remote_code=True`.
Note that `config.json` has been set to a sequence length of 8192. This can be modified to 4096 if you want to try with a smaller sequence length.
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/Chronos-Hermes-13B-SuperHOT-8K-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU inference](https://huggingface.co/TheBloke/Chronos-Hermes-13B-SuperHOT-8K-GGML)
* [Unquantised SuperHOT fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/Chronos-Hermes-13B-SuperHOT-8K-fp16)
* [Unquantised base fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/Austism/chronos-hermes-13b)
## How to use this model from Python code
First make sure you have Einops installed:
```
pip3 install auto-gptq
```
Then run the following code. `config.json` has been default to a sequence length of 8192, but you can also configure this in your Python code.
The provided modelling code, activated with `trust_remote_code=True` will automatically set the `scale` parameter from the configured `max_position_embeddings`. Eg for 8192, `scale` is set to `4`.
```python
from transformers import AutoConfig, AutoTokenizer, AutoModelForCausalLM, pipeline
import argparse
model_name_or_path = "TheBloke/Chronos-Hermes-13B-SuperHOT-8K-fp16"
use_triton = False
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
config = AutoConfig.from_pretrained(model_name_or_path, trust_remote_code=True)
# Change this to the sequence length you want
config.max_position_embeddings = 8192
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
config=config,
trust_remote_code=True,
device_map='auto')
# Note: check to confirm if this is correct prompt template is correct for this model!
prompt = "Tell me about AI"
prompt_template=f'''USER: {prompt}
ASSISTANT:'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
temperature=0.7,
top_p=0.95,
repetition_penalty=1.15
)
print(pipe(prompt_template)[0]['generated_text'])
```
## Using other UIs: monkey patch
Provided in the repo is `llama_rope_scaled_monkey_patch.py`, written by @kaiokendev.
It can be theoretically be added to any Python UI or custom code to enable the same result as `trust_remote_code=True`. I have not tested this, and it should be superseded by using `trust_remote_code=True`, but I include it for completeness and for interest.
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: zynix , ya boyyy, Trenton Dambrowitz, Imad Khwaja, Alps Aficionado, chris gileta, John Detwiler, Willem Michiel, RoA, Mano Prime, Rainer Wilmers, Fred von Graf, Matthew Berman, Ghost , Nathan LeClaire, Iucharbius , Ai Maven, Illia Dulskyi, Joseph William Delisle, Space Cruiser, Lone Striker, Karl Bernard, Eugene Pentland, Greatston Gnanesh, Jonathan Leane, Randy H, Pierre Kircher, Willian Hasse, Stephen Murray, Alex , terasurfer , Edmond Seymore, Oscar Rangel, Luke Pendergrass, Asp the Wyvern, Junyu Yang, David Flickinger, Luke, Spiking Neurons AB, subjectnull, Pyrater, Nikolai Manek, senxiiz, Ajan Kanaga, Johann-Peter Hartmann, Artur Olbinski, Kevin Schuppel, Derek Yates, Kalila, K, Talal Aujan, Khalefa Al-Ahmad, Gabriel Puliatti, John Villwock, WelcomeToTheClub, Daniel P. Andersen, Preetika Verma, Deep Realms, Fen Risland, trip7s trip, webtim, Sean Connelly, Michael Levine, Chris McCloskey, biorpg, vamX, Viktor Bowallius, Cory Kujawski.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: Kaio Ken's SuperHOT 8K
### SuperHOT Prototype 2 w/ 8K Context
This is a second prototype of SuperHOT, this time 30B with 8K context and no RLHF, using the same technique described in [the github blog](https://kaiokendev.github.io/til#extending-context-to-8k).
Tests have shown that the model does indeed leverage the extended context at 8K.
You will need to **use either the monkeypatch** or, if you are already using the monkeypatch, **change the scaling factor to 0.25 and the maximum sequence length to 8192**
#### Looking for Merged & Quantized Models?
- 30B 4-bit CUDA: [tmpupload/superhot-30b-8k-4bit-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-safetensors)
- 30B 4-bit CUDA 128g: [tmpupload/superhot-30b-8k-4bit-128g-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-128g-safetensors)
#### Training Details
I trained the LoRA with the following configuration:
- 1200 samples (~400 samples over 2048 sequence length)
- learning rate of 3e-4
- 3 epochs
- The exported modules are:
- q_proj
- k_proj
- v_proj
- o_proj
- no bias
- Rank = 4
- Alpha = 8
- no dropout
- weight decay of 0.1
- AdamW beta1 of 0.9 and beta2 0.99, epsilon of 1e-5
- Trained on 4-bit base model
# Original model card: Austism's Chronos Hermes 13B
([chronos-13b](https://huggingface.co/elinas/chronos-13b) + [Nous-Hermes-13b](https://huggingface.co/NousResearch/Nous-Hermes-13b)) 75/25 merge
This has the aspects of chronos's nature to produce long, descriptive outputs. But with additional coherency and an ability to better obey instructions. Resulting in this model having a great ability to produce proactive storywriting and follow a narrative.
This mix contains alot of chronos's writing style and 'flavour' with far less tendency of going AWOL and spouting nonsensical babble.
This result was much more successful than my [first chronos merge](https://huggingface.co/Austism/chronos-wizardlm-uc-scot-st-13b).
|
TheBloke/Wizard-Vicuna-13B-Uncensored-SuperHOT-8K-fp16 | TheBloke | "2023-07-09T20:24:50Z" | 19 | 18 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"custom_code",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-06-27T03:55:57Z" | ---
inference: false
license: other
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# Eric Hartford's Wizard Vicuna 13B Uncensored fp16
This is fp16 pytorch format model files for [Eric Hartford's Wizard Vicuna 13B Uncensored](https://huggingface.co/ehartford/Wizard-Vicuna-13B-Uncensored) merged with [Kaio Ken's SuperHOT 8K](https://huggingface.co/kaiokendev/superhot-13b-8k-no-rlhf-test).
[Kaio Ken's SuperHOT 13b LoRA](https://huggingface.co/kaiokendev/superhot-13b-8k-no-rlhf-test) is merged on to the base model, and then 8K context can be achieved during inference by using `trust_remote_code=True`.
Note that `config.json` has been set to a sequence length of 8192. This can be modified to 4096 if you want to try with a smaller sequence length.
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/Wizard-Vicuna-13B-Uncensored-SuperHOT-8K-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU inference](https://huggingface.co/TheBloke/Wizard-Vicuna-13B-Uncensored-SuperHOT-8K-GGML)
* [Unquantised SuperHOT fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/Wizard-Vicuna-13B-Uncensored-SuperHOT-8K-fp16)
* [Unquantised base fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/ehartford/Wizard-Vicuna-13B-Uncensored)
## How to use this model from Python code
First make sure you have Einops installed:
```
pip3 install auto-gptq
```
Then run the following code. `config.json` has been default to a sequence length of 8192, but you can also configure this in your Python code.
The provided modelling code, activated with `trust_remote_code=True` will automatically set the `scale` parameter from the configured `max_position_embeddings`. Eg for 8192, `scale` is set to `4`.
```python
from transformers import AutoConfig, AutoTokenizer, AutoModelForCausalLM, pipeline
import argparse
model_name_or_path = "TheBloke/Wizard-Vicuna-13B-Uncensored-SuperHOT-8K-fp16"
use_triton = False
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
config = AutoConfig.from_pretrained(model_name_or_path, trust_remote_code=True)
# Change this to the sequence length you want
config.max_position_embeddings = 8192
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
config=config,
trust_remote_code=True,
device_map='auto')
# Note: check to confirm if this is correct prompt template is correct for this model!
prompt = "Tell me about AI"
prompt_template=f'''USER: {prompt}
ASSISTANT:'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
temperature=0.7,
top_p=0.95,
repetition_penalty=1.15
)
print(pipe(prompt_template)[0]['generated_text'])
```
## Using other UIs: monkey patch
Provided in the repo is `llama_rope_scaled_monkey_patch.py`, written by @kaiokendev.
It can be theoretically be added to any Python UI or custom code to enable the same result as `trust_remote_code=True`. I have not tested this, and it should be superseded by using `trust_remote_code=True`, but I include it for completeness and for interest.
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: zynix , ya boyyy, Trenton Dambrowitz, Imad Khwaja, Alps Aficionado, chris gileta, John Detwiler, Willem Michiel, RoA, Mano Prime, Rainer Wilmers, Fred von Graf, Matthew Berman, Ghost , Nathan LeClaire, Iucharbius , Ai Maven, Illia Dulskyi, Joseph William Delisle, Space Cruiser, Lone Striker, Karl Bernard, Eugene Pentland, Greatston Gnanesh, Jonathan Leane, Randy H, Pierre Kircher, Willian Hasse, Stephen Murray, Alex , terasurfer , Edmond Seymore, Oscar Rangel, Luke Pendergrass, Asp the Wyvern, Junyu Yang, David Flickinger, Luke, Spiking Neurons AB, subjectnull, Pyrater, Nikolai Manek, senxiiz, Ajan Kanaga, Johann-Peter Hartmann, Artur Olbinski, Kevin Schuppel, Derek Yates, Kalila, K, Talal Aujan, Khalefa Al-Ahmad, Gabriel Puliatti, John Villwock, WelcomeToTheClub, Daniel P. Andersen, Preetika Verma, Deep Realms, Fen Risland, trip7s trip, webtim, Sean Connelly, Michael Levine, Chris McCloskey, biorpg, vamX, Viktor Bowallius, Cory Kujawski.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: Kaio Ken's SuperHOT 8K
### SuperHOT Prototype 2 w/ 8K Context
This is a second prototype of SuperHOT, this time 30B with 8K context and no RLHF, using the same technique described in [the github blog](https://kaiokendev.github.io/til#extending-context-to-8k).
Tests have shown that the model does indeed leverage the extended context at 8K.
You will need to **use either the monkeypatch** or, if you are already using the monkeypatch, **change the scaling factor to 0.25 and the maximum sequence length to 8192**
#### Looking for Merged & Quantized Models?
- 30B 4-bit CUDA: [tmpupload/superhot-30b-8k-4bit-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-safetensors)
- 30B 4-bit CUDA 128g: [tmpupload/superhot-30b-8k-4bit-128g-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-128g-safetensors)
#### Training Details
I trained the LoRA with the following configuration:
- 1200 samples (~400 samples over 2048 sequence length)
- learning rate of 3e-4
- 3 epochs
- The exported modules are:
- q_proj
- k_proj
- v_proj
- o_proj
- no bias
- Rank = 4
- Alpha = 8
- no dropout
- weight decay of 0.1
- AdamW beta1 of 0.9 and beta2 0.99, epsilon of 1e-5
- Trained on 4-bit base model
# Original model card: Eric Hartford's Wizard Vicuna 13B Uncensored
This is [wizard-vicuna-13b](https://huggingface.co/junelee/wizard-vicuna-13b) trained with a subset of the dataset - responses that contained alignment / moralizing were removed. The intent is to train a WizardLM that doesn't have alignment built-in, so that alignment (of any sort) can be added separately with for example with a RLHF LoRA.
Shout out to the open source AI/ML community, and everyone who helped me out.
Note:
An uncensored model has no guardrails.
You are responsible for anything you do with the model, just as you are responsible for anything you do with any dangerous object such as a knife, gun, lighter, or car.
Publishing anything this model generates is the same as publishing it yourself.
You are responsible for the content you publish, and you cannot blame the model any more than you can blame the knife, gun, lighter, or car for what you do with it.
|
TheBloke/Robin-13B-v2-SuperHOT-8K-fp16 | TheBloke | "2023-07-09T20:24:49Z" | 9 | 1 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"custom_code",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-06-27T01:53:00Z" | ---
inference: false
license: other
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# OptimalScale's Robin 13B v2 fp16
This is fp16 pytorch format model files for [OptimalScale's Robin 13B v2](https://huggingface.co/TheBloke/robin-13B-v2-fp16) merged with [Kaio Ken's SuperHOT 8K](https://huggingface.co/kaiokendev/superhot-13b-8k-no-rlhf-test).
[Kaio Ken's SuperHOT 13b LoRA](https://huggingface.co/kaiokendev/superhot-13b-8k-no-rlhf-test) is merged on to the base model, and then 8K context can be achieved during inference by using `trust_remote_code=True`.
Note that `config.json` has been set to a sequence length of 8192. This can be modified to 4096 if you want to try with a smaller sequence length.
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/Robin-13B-v2-SuperHOT-8K-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU inference](https://huggingface.co/TheBloke/Robin-13B-v2-SuperHOT-8K-GGML)
* [Unquantised SuperHOT fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/Robin-13B-v2-SuperHOT-8K-fp16)
* [Unquantised base fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/OptimalScale/robin-13b-v2-delta)
## How to use this model from Python code
First make sure you have Einops installed:
```
pip3 install auto-gptq
```
Then run the following code. `config.json` has been default to a sequence length of 8192, but you can also configure this in your Python code.
The provided modelling code, activated with `trust_remote_code=True` will automatically set the `scale` parameter from the configured `max_position_embeddings`. Eg for 8192, `scale` is set to `4`.
```python
from transformers import AutoConfig, AutoTokenizer, AutoModelForCausalLM, pipeline
import argparse
model_name_or_path = "TheBloke/Robin-13B-v2-SuperHOT-8K-fp16"
use_triton = False
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
config = AutoConfig.from_pretrained(model_name_or_path, trust_remote_code=True)
# Change this to the sequence length you want
config.max_position_embeddings = 8192
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
config=config,
trust_remote_code=True,
device_map='auto')
# Note: check to confirm if this is correct prompt template is correct for this model!
prompt = "Tell me about AI"
prompt_template=f'''USER: {prompt}
ASSISTANT:'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
temperature=0.7,
top_p=0.95,
repetition_penalty=1.15
)
print(pipe(prompt_template)[0]['generated_text'])
```
## Using other UIs: monkey patch
Provided in the repo is `llama_rope_scaled_monkey_patch.py`, written by @kaiokendev.
It can be theoretically be added to any Python UI or custom code to enable the same result as `trust_remote_code=True`. I have not tested this, and it should be superseded by using `trust_remote_code=True`, but I include it for completeness and for interest.
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: zynix , ya boyyy, Trenton Dambrowitz, Imad Khwaja, Alps Aficionado, chris gileta, John Detwiler, Willem Michiel, RoA, Mano Prime, Rainer Wilmers, Fred von Graf, Matthew Berman, Ghost , Nathan LeClaire, Iucharbius , Ai Maven, Illia Dulskyi, Joseph William Delisle, Space Cruiser, Lone Striker, Karl Bernard, Eugene Pentland, Greatston Gnanesh, Jonathan Leane, Randy H, Pierre Kircher, Willian Hasse, Stephen Murray, Alex , terasurfer , Edmond Seymore, Oscar Rangel, Luke Pendergrass, Asp the Wyvern, Junyu Yang, David Flickinger, Luke, Spiking Neurons AB, subjectnull, Pyrater, Nikolai Manek, senxiiz, Ajan Kanaga, Johann-Peter Hartmann, Artur Olbinski, Kevin Schuppel, Derek Yates, Kalila, K, Talal Aujan, Khalefa Al-Ahmad, Gabriel Puliatti, John Villwock, WelcomeToTheClub, Daniel P. Andersen, Preetika Verma, Deep Realms, Fen Risland, trip7s trip, webtim, Sean Connelly, Michael Levine, Chris McCloskey, biorpg, vamX, Viktor Bowallius, Cory Kujawski.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: Kaio Ken's SuperHOT 8K
### SuperHOT Prototype 2 w/ 8K Context
This is a second prototype of SuperHOT, this time 30B with 8K context and no RLHF, using the same technique described in [the github blog](https://kaiokendev.github.io/til#extending-context-to-8k).
Tests have shown that the model does indeed leverage the extended context at 8K.
You will need to **use either the monkeypatch** or, if you are already using the monkeypatch, **change the scaling factor to 0.25 and the maximum sequence length to 8192**
#### Looking for Merged & Quantized Models?
- 30B 4-bit CUDA: [tmpupload/superhot-30b-8k-4bit-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-safetensors)
- 30B 4-bit CUDA 128g: [tmpupload/superhot-30b-8k-4bit-128g-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-128g-safetensors)
#### Training Details
I trained the LoRA with the following configuration:
- 1200 samples (~400 samples over 2048 sequence length)
- learning rate of 3e-4
- 3 epochs
- The exported modules are:
- q_proj
- k_proj
- v_proj
- o_proj
- no bias
- Rank = 4
- Alpha = 8
- no dropout
- weight decay of 0.1
- AdamW beta1 of 0.9 and beta2 0.99, epsilon of 1e-5
- Trained on 4-bit base model
# Original model card: OptimalScale's Robin 13B v2
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/Jq4vkcDakD">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# OptimalScale's Robin 13B v2 fp16
These files are pytorch format fp16 model files for [OptimalScale's Robin 13B v2](https://huggingface.co/OptimalScale/robin-13b-v2-delta).
It is the result of merging and/or converting the source repository to float16.
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/robin-13B-v2-fp16)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/robin-13B-v2-GGML)
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/robin-13B-v2-fp16)
## Prompt template
```
A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions
###Human: prompt
###Assistant:
```
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/Jq4vkcDakD)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: vamX, K, Jonathan Leane, Lone Striker, Sean Connelly, Chris McCloskey, WelcomeToTheClub, Nikolai Manek, John Detwiler, Kalila, David Flickinger, Fen Risland, subjectnull, Johann-Peter Hartmann, Talal Aujan, John Villwock, senxiiz, Khalefa Al-Ahmad, Kevin Schuppel, Alps Aficionado, Derek Yates, Mano Prime, Nathan LeClaire, biorpg, trip7s trip, Asp the Wyvern, chris gileta, Iucharbius , Artur Olbinski, Ai Maven, Joseph William Delisle, Luke Pendergrass, Illia Dulskyi, Eugene Pentland, Ajan Kanaga, Willem Michiel, Space Cruiser, Pyrater, Preetika Verma, Junyu Yang, Oscar Rangel, Spiking Neurons AB, Pierre Kircher, webtim, Cory Kujawski, terasurfer , Trenton Dambrowitz, Gabriel Puliatti, Imad Khwaja, Luke.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: OptimalScale's Robin 13B v2
No model card provided in source repository.
|
TheBloke/Manticore-13B-SuperHOT-8K-fp16 | TheBloke | "2023-07-09T20:24:48Z" | 9 | 1 | transformers | [
"transformers",
"pytorch",
"llama",
"text-generation",
"custom_code",
"license:other",
"autotrain_compatible",
"text-generation-inference",
"region:us"
] | text-generation | "2023-06-27T00:45:15Z" | ---
inference: false
license: other
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# OpenAccess AI Collective's Manticore 13B fp16
This is fp16 pytorch format model files for [OpenAccess AI Collective's Manticore 13B](https://huggingface.co/openaccess-ai-collective/manticore-13b) merged with [Kaio Ken's SuperHOT 8K](https://huggingface.co/kaiokendev/superhot-13b-8k-no-rlhf-test).
[Kaio Ken's SuperHOT 13b LoRA](https://huggingface.co/kaiokendev/superhot-13b-8k-no-rlhf-test) is merged on to the base model, and then 8K context can be achieved during inference by using `trust_remote_code=True`.
Note that `config.json` has been set to a sequence length of 8192. This can be modified to 4096 if you want to try with a smaller sequence length.
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/Manticore-13B-SuperHOT-8K-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU inference](https://huggingface.co/TheBloke/Manticore-13B-SuperHOT-8K-GGML)
* [Unquantised SuperHOT fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/TheBloke/Manticore-13B-SuperHOT-8K-fp16)
* [Unquantised base fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/openaccess-ai-collective/manticore-13b)
## How to use this model from Python code
First make sure you have Einops installed:
```
pip3 install auto-gptq
```
Then run the following code. `config.json` has been default to a sequence length of 8192, but you can also configure this in your Python code.
The provided modelling code, activated with `trust_remote_code=True` will automatically set the `scale` parameter from the configured `max_position_embeddings`. Eg for 8192, `scale` is set to `4`.
```python
from transformers import AutoConfig, AutoTokenizer, AutoModelForCausalLM, pipeline
import argparse
model_name_or_path = "TheBloke/Manticore-13B-SuperHOT-8K-fp16"
use_triton = False
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, use_fast=True)
config = AutoConfig.from_pretrained(model_name_or_path, trust_remote_code=True)
# Change this to the sequence length you want
config.max_position_embeddings = 8192
model = AutoModelForCausalLM.from_pretrained(model_name_or_path,
config=config,
trust_remote_code=True,
device_map='auto')
# Note: check to confirm if this is correct prompt template is correct for this model!
prompt = "Tell me about AI"
prompt_template=f'''USER: {prompt}
ASSISTANT:'''
print("\n\n*** Generate:")
input_ids = tokenizer(prompt_template, return_tensors='pt').input_ids.cuda()
output = model.generate(inputs=input_ids, temperature=0.7, max_new_tokens=512)
print(tokenizer.decode(output[0]))
# Inference can also be done using transformers' pipeline
print("*** Pipeline:")
pipe = pipeline(
"text-generation",
model=model,
tokenizer=tokenizer,
max_new_tokens=512,
temperature=0.7,
top_p=0.95,
repetition_penalty=1.15
)
print(pipe(prompt_template)[0]['generated_text'])
```
## Using other UIs: monkey patch
Provided in the repo is `llama_rope_scaled_monkey_patch.py`, written by @kaiokendev.
It can be theoretically be added to any Python UI or custom code to enable the same result as `trust_remote_code=True`. I have not tested this, and it should be superseded by using `trust_remote_code=True`, but I include it for completeness and for interest.
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: zynix , ya boyyy, Trenton Dambrowitz, Imad Khwaja, Alps Aficionado, chris gileta, John Detwiler, Willem Michiel, RoA, Mano Prime, Rainer Wilmers, Fred von Graf, Matthew Berman, Ghost , Nathan LeClaire, Iucharbius , Ai Maven, Illia Dulskyi, Joseph William Delisle, Space Cruiser, Lone Striker, Karl Bernard, Eugene Pentland, Greatston Gnanesh, Jonathan Leane, Randy H, Pierre Kircher, Willian Hasse, Stephen Murray, Alex , terasurfer , Edmond Seymore, Oscar Rangel, Luke Pendergrass, Asp the Wyvern, Junyu Yang, David Flickinger, Luke, Spiking Neurons AB, subjectnull, Pyrater, Nikolai Manek, senxiiz, Ajan Kanaga, Johann-Peter Hartmann, Artur Olbinski, Kevin Schuppel, Derek Yates, Kalila, K, Talal Aujan, Khalefa Al-Ahmad, Gabriel Puliatti, John Villwock, WelcomeToTheClub, Daniel P. Andersen, Preetika Verma, Deep Realms, Fen Risland, trip7s trip, webtim, Sean Connelly, Michael Levine, Chris McCloskey, biorpg, vamX, Viktor Bowallius, Cory Kujawski.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: Kaio Ken's SuperHOT 8K
### SuperHOT Prototype 2 w/ 8K Context
This is a second prototype of SuperHOT, this time 30B with 8K context and no RLHF, using the same technique described in [the github blog](https://kaiokendev.github.io/til#extending-context-to-8k).
Tests have shown that the model does indeed leverage the extended context at 8K.
You will need to **use either the monkeypatch** or, if you are already using the monkeypatch, **change the scaling factor to 0.25 and the maximum sequence length to 8192**
#### Looking for Merged & Quantized Models?
- 30B 4-bit CUDA: [tmpupload/superhot-30b-8k-4bit-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-safetensors)
- 30B 4-bit CUDA 128g: [tmpupload/superhot-30b-8k-4bit-128g-safetensors](https://huggingface.co/tmpupload/superhot-30b-8k-4bit-128g-safetensors)
#### Training Details
I trained the LoRA with the following configuration:
- 1200 samples (~400 samples over 2048 sequence length)
- learning rate of 3e-4
- 3 epochs
- The exported modules are:
- q_proj
- k_proj
- v_proj
- o_proj
- no bias
- Rank = 4
- Alpha = 8
- no dropout
- weight decay of 0.1
- AdamW beta1 of 0.9 and beta2 0.99, epsilon of 1e-5
- Trained on 4-bit base model
# Original model card: OpenAccess AI Collective's Manticore 13B
# Manticore 13B - (previously Wizard Mega)
**[💵 Donate to OpenAccess AI Collective](https://github.com/sponsors/OpenAccess-AI-Collective) to help us keep building great tools and models!**
Questions, comments, feedback, looking to donate, or want to help? Reach out on our [Discord](https://discord.gg/EqrvvehG) or email [wing@openaccessaicollective.org](mailto:wing@openaccessaicollective.org)
Manticore 13B is a Llama 13B model fine-tuned on the following datasets:
- [ShareGPT](https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered) - based on a cleaned and de-suped subset
- [WizardLM](https://huggingface.co/datasets/ehartford/WizardLM_alpaca_evol_instruct_70k_unfiltered)
- [Wizard-Vicuna](https://huggingface.co/datasets/ehartford/wizard_vicuna_70k_unfiltered)
- [subset of QingyiSi/Alpaca-CoT for roleplay and CoT](https://huggingface.co/QingyiSi/Alpaca-CoT)
- [GPT4-LLM-Cleaned](https://huggingface.co/datasets/teknium/GPT4-LLM-Cleaned)
- [GPTeacher-General-Instruct](https://huggingface.co/datasets/teknium/GPTeacher-General-Instruct)
- ARC-Easy & ARC-Challenge - instruct augmented for detailed responses
- mmlu: instruct augmented for detailed responses subset including
- abstract_algebra
- conceptual_physics
- formal_logic
- high_school_physics
- logical_fallacies
- [hellaswag](https://huggingface.co/datasets/hellaswag) - 5K row subset of instruct augmented for concise responses
- [metaeval/ScienceQA_text_only](https://huggingface.co/datasets/metaeval/ScienceQA_text_only) - instruct for concise responses
- [openai/summarize_from_feedback](https://huggingface.co/datasets/openai/summarize_from_feedback) - instruct augmented tl;dr summarization
# Demo
Try out the model in HF Spaces. The demo uses a quantized GGML version of the model to quickly return predictions on smaller GPUs (and even CPUs). Quantized GGML may have some minimal loss of model quality.
- https://huggingface.co/spaces/openaccess-ai-collective/manticore-ggml
## Release Notes
- https://wandb.ai/wing-lian/manticore-13b/runs/nq3u3uoh/workspace
## Build
Manticore was built with [Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) on 8xA100 80GB
- Preview Release: 3 epochs taking approximately 24 hours.
- The configuration to duplicate this build is provided in this repo's [/config folder](https://huggingface.co/openaccess-ai-collective/manticore-13b/tree/main/configs).
## Bias, Risks, and Limitations
Manticore has not been aligned to human preferences with techniques like RLHF or deployed with in-the-loop filtering of responses like ChatGPT, so the model can produce problematic outputs (especially when prompted to do so).
Manticore was fine-tuned from the base model LlaMa 13B, please refer to its model card's Limitations Section for relevant information.
## Examples
````
### Instruction: write Python code that returns the first n numbers of the Fibonacci sequence using memoization.
### Assistant:
Here’s an example of how you can use memoization to efficiently calculate the first n numbers of the Fibonacci sequence in Python:
```
def fib(n):
# Memoize the last calculated Fibonacci number for each index
cache = {}
def fib_memoized(n):
if n not in cache:
cache[n] = [0, 1]
else:
return cache[n][-1], cache[n][-2]
# Recursive helper function to calculate the Fibonacci sequence up to a given index
def fib_helper(n):
if n == 0 or n == 1:
return 0, 1
else:
return fib_helper(n - 1) + fib_helper(n - 2)
# Calculate the first n numbers of the Fibonacci sequence using memoization
def fib_memoized_seq(n):
if n == 0 or n == 1:
return 0, 1
else:
result = fib_helper(n - 1) + fib_helper(n - 2)
cache[n] = [result]
return result, cache[n][-1], cache[n][-2]
# Example usage
for i in range(len(fib_memoized_seq(3))):
print(fib_memoized_seq(3)[i])
```
In this implementation, we use a cache dictionary to memoize the last calculated Fibonacci number for each index. We define two helper functions: fib_helper, which recursively calculates the Fibonacci sequence up to a given index, and fib_memoized, which uses memoization to efficiently calculate the first n numbers of the Fibonacci sequence. Finally, we define the fib_memoized_seq function, which is our main function for calculating the first n numbers of the Fibonacci sequence using memoization.
````
```
USER: Finish the joke, a mechanic and a car salesman walk into a bar...
ASSISTANT: … and when they get up to leave, they realize that they’ve left their keys in their cars. The mechanic says “I know how to fix this” and opens his toolbox to grab something. Then he stops and looks at the salesman. He says “You drive a Toyota, right?” The salesman nods. The mechanic then takes out a tiny screwdriver from his toolbox and starts working on the lock of the car door. The salesman is amazed and asks how he knew that. The mechanic replies “I can tell by the way you parked your car.”
```
```
USER: Describe how a tsunami would affect the residents of Denver Colorado
ASSISTANT: The impact of a tsunami in Denver, Colorado would likely be minimal. As there are no coastal areas or bodies of water nearby, a tsunami generated from an earthquake or volcanic activity elsewhere in the world would have little effect on the city and its residents. Even if a large tsunami were to hit the coastline of California or Mexico, the distance between Denver and these locations means that any impacts on the city itself would be minimal.
```
```
USER: If you could do one thing right now, what would it be?
ASSISTANT: I’d hug my loved ones a little tighter today and tell them how much they mean to me.
USER: And who are your loved ones?
ASSISTANT: My closest friends and family members.
USER: What are their names?
ASSISTANT: My two best friends are named Emily and Jessica, my mom is Mary, and my dad is David. Answering the question with a bit more information about who they are or what they mean to me would help provide a more personalized response.
```
|
hopkins/eng-mya-nng | hopkins | "2023-07-09T20:22:27Z" | 103 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"mbart",
"text2text-generation",
"translation",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | translation | "2023-07-09T20:01:22Z" | ---
tags:
- translation
- generated_from_trainer
metrics:
- bleu
model-index:
- name: eng-mya-nng
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# eng-mya-nng
This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.8452
- Bleu: 4.4887
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.26.1
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
mvasiliniuc/iva-codeint-swift-small | mvasiliniuc | "2023-07-09T20:22:26Z" | 15 | 1 | transformers | [
"transformers",
"pytorch",
"gpt2",
"text-generation",
"code",
"swift",
"mobile",
"generation",
"dataset:mvasiliniuc/iva-swift-codeint-clean-train",
"dataset:mvasiliniuc/iva-swift-codeint-clean-valid",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | "2023-06-03T07:17:46Z" | ---
datasets:
- mvasiliniuc/iva-swift-codeint-clean-train
- mvasiliniuc/iva-swift-codeint-clean-valid
language:
- code
tags:
- gpt2
- code
- swift
- mobile
- generation
widget:
- text: "/*\n A function that returns the time zone currently configured on the device.\n*/\n"
example_title: "Get the current time zone of the device"
- text: "/*\n A function that returns the current version of the operating system.\n*/\n"
example_title: "Get current device operating system"
- text: "/* \nA function that fires an NSNotification named 'MyUpdate'. \n*/\npublic func post"
example_title: "Post NSNotification"
- text: "/* \nA public function that saves a given String value in UserPreference at a given String key.\n*/\n"
example_title: "Save to UserPreference"
---
iva-codeint-swift-small GPT-2 is (small version - 239.4M parameters) trained from scratch to obtain results in the text-to-code task tailored for Swift language used
in native mobile development (iOS).
## Usage
```Python
from transformers import pipeline
pipe = pipeline("text-generation", model="mvasiliniuc/iva-codeint-swift-small")
outputs = pipe("func triggerNSNotification")
```
### Inference
```Python
API_URL = "https://api-inference.huggingface.co/models/mvasiliniuc/iva-codeint-swift-small"
headers = {"Authorization": "Bearer <key>"}
def query(payload):
response = requests.post(API_URL, headers=headers, json=payload)
return response.json()
output = query({
"inputs": """
/*
A function that gets the current device operating system.
*/
"""
})
pprint.pprint(output, compact=True)
```
## Training
| Config | Value |
|------|------------------|
| seq length | 1024 |
| weight decay | 0.1 |
| learning rate | 0.0005 |
| max eval steps | -1 |
| shuffle buffer | 10000 |
| max train steps | 150000 |
| mixed precision | fp16 |
| num warmup steps | 2000 |
| train batch size | 5 |
| valid batch size | 5 |
| lr scheduler type | cosine |
| save checkpoint steps | 15000 |
| gradient checkpointing | false |
| gradient accumulation steps | 1 |
## Resources
Resources used for research:
* [Training a causal language model from scratch](https://huggingface.co/learn/nlp-course/chapter7/6)
* [CodeParrot a GPT-2 model (1.5B parameters) trained to generate Python code](https://huggingface.co/codeparrot/codeparrot)
|
tianamonthe1/_1 | tianamonthe1 | "2023-07-09T20:10:38Z" | 0 | 0 | null | [
"arxiv:1910.09700",
"license:cc",
"region:us"
] | null | "2023-07-09T20:07:40Z" | ---
license: cc
---
# Model Card for Model ID
<!-- Provide a quick summary of what the model is/does. -->
This modelcard aims to be a base template for new models. It has been generated using [this raw template](https://github.com/huggingface/huggingface_hub/blob/main/src/huggingface_hub/templates/modelcard_template.md?plain=1).
## Model Details
### Model Description
<!-- Provide a longer summary of what this model is. -->
- **Developed by:** [More Information Needed]
- **Shared by [optional]:** [More Information Needed]
- **Model type:** [More Information Needed]
- **Language(s) (NLP):** [More Information Needed]
- **License:** [More Information Needed]
- **Finetuned from model [optional]:** [More Information Needed]
### Model Sources [optional]
<!-- Provide the basic links for the model. -->
- **Repository:** [More Information Needed]
- **Paper [optional]:** [More Information Needed]
- **Demo [optional]:** [More Information Needed]
## Uses
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
### Direct Use
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
[More Information Needed]
### Downstream Use [optional]
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
[More Information Needed]
### Out-of-Scope Use
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
[More Information Needed]
## Bias, Risks, and Limitations
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
[More Information Needed]
### Recommendations
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
## How to Get Started with the Model
Use the code below to get started with the model.
[More Information Needed]
## Training Details
### Training Data
<!-- This should link to a Data Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
[More Information Needed]
### Training Procedure
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
#### Preprocessing [optional]
[More Information Needed]
#### Training Hyperparameters
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
#### Speeds, Sizes, Times [optional]
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
[More Information Needed]
## Evaluation
<!-- This section describes the evaluation protocols and provides the results. -->
### Testing Data, Factors & Metrics
#### Testing Data
<!-- This should link to a Data Card if possible. -->
[More Information Needed]
#### Factors
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
[More Information Needed]
#### Metrics
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
[More Information Needed]
### Results
[More Information Needed]
#### Summary
## Model Examination [optional]
<!-- Relevant interpretability work for the model goes here -->
[More Information Needed]
## Environmental Impact
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
- **Hardware Type:** [More Information Needed]
- **Hours used:** [More Information Needed]
- **Cloud Provider:** [More Information Needed]
- **Compute Region:** [More Information Needed]
- **Carbon Emitted:** [More Information Needed]
## Technical Specifications [optional]
### Model Architecture and Objective
[More Information Needed]
### Compute Infrastructure
[More Information Needed]
#### Hardware
[More Information Needed]
#### Software
[More Information Needed]
## Citation [optional]
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
**BibTeX:**
[More Information Needed]
**APA:**
[More Information Needed]
## Glossary [optional]
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
[More Information Needed]
## More Information [optional]
[More Information Needed]
## Model Card Authors [optional]
[More Information Needed]
## Model Card Contact
[More Information Needed]
|
RomaNest/ppo-Huggy | RomaNest | "2023-07-09T20:06:10Z" | 7 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] | reinforcement-learning | "2023-07-09T20:06:05Z" | ---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: RomaNest/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
hopkins/eng-kor-nng | hopkins | "2023-07-09T20:06:01Z" | 105 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"mbart",
"text2text-generation",
"translation",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | translation | "2023-07-09T19:46:56Z" | ---
tags:
- translation
- generated_from_trainer
metrics:
- bleu
model-index:
- name: eng-kor-nng
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# eng-kor-nng
This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.0136
- Bleu: 6.2476
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.26.1
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
tyavika/lr_1e5_Distil-CNN256LSTM128NoBi | tyavika | "2023-07-09T20:02:54Z" | 77 | 0 | transformers | [
"transformers",
"pytorch",
"distilbert",
"question-answering",
"generated_from_trainer",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | question-answering | "2023-07-07T04:08:59Z" | ---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: lr_1e5_Distil-CNN256LSTM128NoBi
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# lr_1e5_Distil-CNN256LSTM128NoBi
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5121
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 3e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 2.0386 | 1.0 | 3290 | 1.8344 |
| 1.3189 | 2.0 | 6580 | 1.3399 |
| 0.8649 | 3.0 | 9870 | 1.2492 |
| 0.6271 | 4.0 | 13160 | 1.2992 |
| 0.4302 | 5.0 | 16450 | 1.5121 |
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
skywalker7/ppo-Huggy | skywalker7 | "2023-07-09T19:55:54Z" | 1 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] | reinforcement-learning | "2023-07-09T19:55:51Z" | ---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: skywalker7/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
dp15/poca-SoccerTwosv2 | dp15 | "2023-07-09T19:50:02Z" | 1 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"SoccerTwos",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SoccerTwos",
"region:us"
] | reinforcement-learning | "2023-07-09T19:45:35Z" | ---
library_name: ml-agents
tags:
- SoccerTwos
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SoccerTwos
---
# **poca** Agent playing **SoccerTwos**
This is a trained model of a **poca** agent playing **SoccerTwos**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: dp15/poca-SoccerTwosv2
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
hopkins/eng-guj-nng | hopkins | "2023-07-09T19:41:19Z" | 102 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"mbart",
"text2text-generation",
"translation",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | translation | "2023-07-09T19:19:37Z" | ---
tags:
- translation
- generated_from_trainer
metrics:
- bleu
model-index:
- name: eng-guj-nng
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# eng-guj-nng
This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.2276
- Bleu: 2.8879
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.26.1
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
hopkins/eng-ind-nng | hopkins | "2023-07-09T19:35:41Z" | 102 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"mbart",
"text2text-generation",
"translation",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | translation | "2023-07-09T19:18:00Z" | ---
tags:
- translation
- generated_from_trainer
metrics:
- bleu
model-index:
- name: eng-ind-nng
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# eng-ind-nng
This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.7826
- Bleu: 20.9168
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.26.1
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
RogerB/deberta-base-finetuned-kintweetsE | RogerB | "2023-07-09T19:29:34Z" | 105 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"deberta",
"fill-mask",
"generated_from_trainer",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | "2023-07-09T19:09:39Z" | ---
license: mit
tags:
- generated_from_trainer
model-index:
- name: deberta-base-finetuned-kintweetsE
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# deberta-base-finetuned-kintweetsE
This model is a fine-tuned version of [microsoft/deberta-base](https://huggingface.co/microsoft/deberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.4010
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 10
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 4.7396 | 1.0 | 1000 | 3.9160 |
| 3.7652 | 2.0 | 2000 | 3.4778 |
| 3.5318 | 3.0 | 3000 | 3.3727 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
dp15/poca-SoccerTwos | dp15 | "2023-07-09T19:28:19Z" | 1 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"SoccerTwos",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SoccerTwos",
"region:us"
] | reinforcement-learning | "2023-07-09T17:03:18Z" | ---
library_name: ml-agents
tags:
- SoccerTwos
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SoccerTwos
---
# **poca** Agent playing **SoccerTwos**
This is a trained model of a **poca** agent playing **SoccerTwos**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: dp15/poca-SoccerTwos
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
israel-avihail/rl_course_vizdoom_health_gathering_supreme | israel-avihail | "2023-07-09T19:11:32Z" | 0 | 0 | sample-factory | [
"sample-factory",
"tensorboard",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | "2023-07-09T13:11:55Z" | ---
library_name: sample-factory
tags:
- deep-reinforcement-learning
- reinforcement-learning
- sample-factory
model-index:
- name: APPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: doom_health_gathering_supreme
type: doom_health_gathering_supreme
metrics:
- type: mean_reward
value: 10.39 +/- 4.97
name: mean_reward
verified: false
---
A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment.
This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
## Downloading the model
After installing Sample-Factory, download the model with:
```
python -m sample_factory.huggingface.load_from_hub -r israel-avihail/rl_course_vizdoom_health_gathering_supreme
```
## Using the model
To run the model after download, use the `enjoy` script corresponding to this environment:
```
python -m .usr.local.lib.python3.10.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
```
You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
## Training with this model
To continue training with this model, use the `train` script corresponding to this environment:
```
python -m .usr.local.lib.python3.10.dist-packages.ipykernel_launcher --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
```
Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
|
RogerB/xlm-roberta-base-finetuned-kintweetsE | RogerB | "2023-07-09T19:08:26Z" | 103 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"xlm-roberta",
"fill-mask",
"generated_from_trainer",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | "2023-07-09T18:36:00Z" | ---
license: mit
tags:
- generated_from_trainer
model-index:
- name: xlm-roberta-base-finetuned-kintweetsE
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# xlm-roberta-base-finetuned-kintweetsE
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.9498
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 10
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 3.7175 | 1.0 | 1000 | 3.1645 |
| 3.2319 | 2.0 | 2000 | 3.0430 |
| 3.0974 | 3.0 | 3000 | 3.0093 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
hopkins/eng-fra-nng | hopkins | "2023-07-09T19:06:30Z" | 103 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"mbart",
"text2text-generation",
"translation",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | translation | "2023-07-09T18:47:35Z" | ---
tags:
- translation
- generated_from_trainer
metrics:
- bleu
model-index:
- name: eng-fra-nng
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# eng-fra-nng
This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.1352
- Bleu: 32.1574
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.26.1
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
hopkins/eng-deu-nng | hopkins | "2023-07-09T19:05:53Z" | 3 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"mbart",
"text2text-generation",
"translation",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | translation | "2023-07-09T18:47:31Z" | ---
tags:
- translation
- generated_from_trainer
metrics:
- bleu
model-index:
- name: eng-deu-nng
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# eng-deu-nng
This model is a fine-tuned version of [facebook/mbart-large-50-many-to-many-mmt](https://huggingface.co/facebook/mbart-large-50-many-to-many-mmt) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.6582
- Bleu: 20.2230
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
### Training results
### Framework versions
- Transformers 4.26.1
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
JamesVorder/PPO-LunarLander-v2 | JamesVorder | "2023-07-09T19:04:27Z" | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"LunarLander-v2",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | "2023-07-09T19:04:09Z" | ---
library_name: stable-baselines3
tags:
- LunarLander-v2
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: 254.45 +/- 24.22
name: mean_reward
verified: false
---
# **PPO** Agent playing **LunarLander-v2**
This is a trained model of a **PPO** agent playing **LunarLander-v2**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
aryjessen/SkyHawk | aryjessen | "2023-07-09T18:54:28Z" | 0 | 0 | null | [
"text-to-image",
"en",
"region:us"
] | text-to-image | "2023-07-09T18:49:43Z" | ---
language:
- en
pipeline_tag: text-to-image
--- |
guaguale/model_kthv_v2 | guaguale | "2023-07-09T18:49:20Z" | 0 | 0 | diffusers | [
"diffusers",
"tensorboard",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"dreambooth",
"base_model:runwayml/stable-diffusion-v1-5",
"base_model:finetune:runwayml/stable-diffusion-v1-5",
"license:creativeml-openrail-m",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2023-07-09T17:37:42Z" |
---
license: creativeml-openrail-m
base_model: runwayml/stable-diffusion-v1-5
instance_prompt: a male idol sks with blonde hair, wearing a black jacket and fringes on the sides of the jacket
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
- dreambooth
inference: true
---
# DreamBooth - guaguale/model_kthv_v2
This is a dreambooth model derived from runwayml/stable-diffusion-v1-5. The weights were trained on a male idol sks with blonde hair, wearing a black jacket and fringes on the sides of the jacket using [DreamBooth](https://dreambooth.github.io/).
You can find some example images in the following.
DreamBooth for the text encoder was enabled: False.
|
hsc748NLP/GujiRoBERTa_jian_fan | hsc748NLP | "2023-07-09T18:39:46Z" | 447 | 4 | transformers | [
"transformers",
"pytorch",
"bert",
"fill-mask",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | "2023-07-09T17:03:54Z" | ---
tags:
- generated_from_trainer
model-index:
- name: output
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# output
This model is a fine-tuned version of [/gemini/data-1/sikuroberta_vocabtxt](https://huggingface.co//gemini/data-1/sikuroberta_vocabtxt) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 256
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
### Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
hsc748NLP/GujiGPT_jian | hsc748NLP | "2023-07-09T18:38:06Z" | 137 | 1 | transformers | [
"transformers",
"pytorch",
"gpt2",
"text-generation",
"generated_from_trainer",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | "2023-07-09T17:15:19Z" | ---
tags:
- generated_from_trainer
model-index:
- name: output
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# output
This model is a fine-tuned version of [/gemini/data-1/gpt2-chinese-cluecorpussmall](https://huggingface.co//gemini/data-1/gpt2-chinese-cluecorpussmall) on an unknown dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 64
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
### Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
lucasbertola/Reinforce-CartPole | lucasbertola | "2023-07-09T18:36:22Z" | 0 | 0 | null | [
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] | reinforcement-learning | "2023-07-09T15:29:01Z" | ---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-CartPole
results:
- metrics:
- type: mean_reward
value: 494.83 +/- 25.41
name: mean_reward
task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
---
# **Reinforce** Agent playing **CartPole-v1**
This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
aphi/Reinforce-CartPole-v1 | aphi | "2023-07-09T18:24:36Z" | 0 | 0 | null | [
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] | reinforcement-learning | "2023-07-09T18:24:27Z" | ---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-CartPole-v1
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 494.30 +/- 17.10
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **CartPole-v1**
This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
nikolai40/iam-trocr | nikolai40 | "2023-07-09T18:18:53Z" | 46 | 0 | transformers | [
"transformers",
"pytorch",
"vision-encoder-decoder",
"image-text-to-text",
"endpoints_compatible",
"region:us"
] | image-text-to-text | "2023-06-08T10:57:44Z" | ---
metrics:
- trocr
- image-to-text
- CER
---
# TrOCR model fine-tuned on IAM dataset using augmentation (stretching and dilation)
Using [trocr-small-stage1](https://huggingface.co/microsoft/trocr-small-stage1) version |
shoukosagiri/sarasasaionji | shoukosagiri | "2023-07-09T17:58:27Z" | 0 | 0 | null | [
"license:creativeml-openrail-m",
"region:us"
] | null | "2023-07-09T13:05:53Z" | ---
license: creativeml-openrail-m
---
|
RogerB/distilbert-base-uncased-finetuned-kintweetsE | RogerB | "2023-07-09T17:55:15Z" | 124 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"distilbert",
"fill-mask",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | "2023-07-09T17:47:31Z" | ---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: distilbert-base-uncased-finetuned-kintweetsE
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# distilbert-base-uncased-finetuned-kintweetsE
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.1921
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 10
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 3.7016 | 1.0 | 1000 | 3.3955 |
| 3.342 | 2.0 | 2000 | 3.2020 |
| 3.2277 | 3.0 | 3000 | 3.1666 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
cagarraz/LunarLander-v2 | cagarraz | "2023-07-09T17:51:14Z" | 0 | 0 | null | [
"tensorboard",
"LunarLander-v2",
"ppo",
"deep-reinforcement-learning",
"reinforcement-learning",
"custom-implementation",
"deep-rl-course",
"model-index",
"region:us"
] | reinforcement-learning | "2023-07-09T17:51:08Z" | ---
tags:
- LunarLander-v2
- ppo
- deep-reinforcement-learning
- reinforcement-learning
- custom-implementation
- deep-rl-course
model-index:
- name: PPO
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: LunarLander-v2
type: LunarLander-v2
metrics:
- type: mean_reward
value: -172.87 +/- 129.16
name: mean_reward
verified: false
---
# PPO Agent Playing LunarLander-v2
This is a trained model of a PPO agent playing LunarLander-v2.
# Hyperparameters
```python
{'exp_name': 'ppo'
'seed': 1
'torch_deterministic': True
'cuda': True
'track': False
'wandb_project_name': 'cleanRL'
'wandb_entity': None
'capture_video': False
'env_id': 'LunarLander-v2'
'total_timesteps': 50000
'learning_rate': 0.00025
'num_envs': 4
'num_steps': 128
'anneal_lr': True
'gae': True
'gamma': 0.99
'gae_lambda': 0.95
'num_minibatches': 4
'update_epochs': 4
'norm_adv': True
'clip_coef': 0.2
'clip_vloss': True
'ent_coef': 0.01
'vf_coef': 0.5
'max_grad_norm': 0.5
'target_kl': None
'repo_id': 'cagarraz/LunarLander-v2'
'batch_size': 512
'minibatch_size': 128}
```
|
RogerB/bert-base-uncased-finetuned-kintweetsE | RogerB | "2023-07-09T17:46:49Z" | 107 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"bert",
"fill-mask",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | "2023-07-09T17:34:25Z" | ---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: bert-base-uncased-finetuned-kintweetsE
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-base-uncased-finetuned-kintweetsE
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.0631
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 10
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 3.6434 | 1.0 | 1000 | 3.2659 |
| 3.2304 | 2.0 | 2000 | 3.0654 |
| 3.106 | 3.0 | 3000 | 3.0272 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
mrizalf7/t5-small-finetuned-indosum-3 | mrizalf7 | "2023-07-09T17:46:49Z" | 105 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"t5",
"text2text-generation",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text2text-generation | "2023-07-09T16:18:16Z" | ---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: t5-small-finetuned-indosum-3
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# t5-small-finetuned-indosum-3
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 10
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
### Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Hedayat-Abrishami/ppo-Pyramid | Hedayat-Abrishami | "2023-07-09T17:45:06Z" | 0 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"Pyramids",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Pyramids",
"region:us"
] | reinforcement-learning | "2023-07-09T17:44:34Z" | ---
library_name: ml-agents
tags:
- Pyramids
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Pyramids
---
# **ppo** Agent playing **Pyramids**
This is a trained model of a **ppo** agent playing **Pyramids**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: Hedayat-Abrishami/ppo-Pyramid
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
Talha185/my-finance-distilgpt2 | Talha185 | "2023-07-09T17:36:17Z" | 3 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"gpt2",
"text-generation",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | "2023-07-07T12:54:26Z" | ---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: my-finance-distilgpt2
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my-finance-distilgpt2
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.7575
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 1.8687 | 1.0 | 7322 | 1.7943 |
| 1.7948 | 2.0 | 14644 | 1.7666 |
| 1.7736 | 3.0 | 21966 | 1.7575 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
RiadxAvatar/rare-puppers | RiadxAvatar | "2023-07-09T17:33:19Z" | 215 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"vit",
"image-classification",
"huggingpics",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | "2023-07-09T17:33:12Z" | ---
tags:
- image-classification
- pytorch
- huggingpics
metrics:
- accuracy
model-index:
- name: rare-puppers
results:
- task:
name: Image Classification
type: image-classification
metrics:
- name: Accuracy
type: accuracy
value: 0.8484848737716675
---
# rare-puppers
Autogenerated by HuggingPics🤗🖼️
Create your own image classifier for **anything** by running [the demo on Google Colab](https://colab.research.google.com/github/nateraw/huggingpics/blob/main/HuggingPics.ipynb).
Report any issues with the demo at the [github repo](https://github.com/nateraw/huggingpics).
## Example Images
#### corgi
#### samoyed
#### shiba inu
 |
hsc748NLP/GujiRoBERTa_jian | hsc748NLP | "2023-07-09T17:33:12Z" | 125 | 0 | transformers | [
"transformers",
"pytorch",
"bert",
"fill-mask",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | "2023-07-09T17:02:38Z" | ---
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: output
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# output
This model is a fine-tuned version of [/gemini/data-1/chinese-roberta-wwm-ext](https://huggingface.co//gemini/data-1/chinese-roberta-wwm-ext) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.4621
- Accuracy: 0.5242
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 192
- eval_batch_size: 384
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
### Training results
### Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
RogerB/xlm-roberta-large-finetuned-kintweetsE | RogerB | "2023-07-09T17:33:09Z" | 3 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"xlm-roberta",
"fill-mask",
"generated_from_trainer",
"license:mit",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | "2023-07-09T16:29:21Z" | ---
license: mit
tags:
- generated_from_trainer
model-index:
- name: xlm-roberta-large-finetuned-kintweetsE
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# xlm-roberta-large-finetuned-kintweetsE
This model is a fine-tuned version of [xlm-roberta-large](https://huggingface.co/xlm-roberta-large) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.6965
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 10
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 3.2492 | 1.0 | 1000 | 2.8451 |
| 2.8635 | 2.0 | 2000 | 2.7113 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
TheBloke/WizardLM-13B-V1.1-GGML | TheBloke | "2023-07-09T17:27:27Z" | 0 | 35 | null | [
"arxiv:2304.12244",
"license:other",
"region:us"
] | null | "2023-07-07T16:25:24Z" | ---
inference: false
license: other
---
<!-- header start -->
<div style="width: 100%;">
<img src="https://i.imgur.com/EBdldam.jpg" alt="TheBlokeAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
</div>
<div style="display: flex; justify-content: space-between; width: 100%;">
<div style="display: flex; flex-direction: column; align-items: flex-start;">
<p><a href="https://discord.gg/theblokeai">Chat & support: my new Discord server</a></p>
</div>
<div style="display: flex; flex-direction: column; align-items: flex-end;">
<p><a href="https://www.patreon.com/TheBlokeAI">Want to contribute? TheBloke's Patreon page</a></p>
</div>
</div>
<!-- header end -->
# WizardLM's WizardLM 13B V1.1 GGML
These files are GGML format model files for [WizardLM's WizardLM 13B V1.1](https://huggingface.co/WizardLM/WizardLM-13B-V1.1).
GGML files are for CPU + GPU inference using [llama.cpp](https://github.com/ggerganov/llama.cpp) and libraries and UIs which support this format, such as:
* [text-generation-webui](https://github.com/oobabooga/text-generation-webui)
* [KoboldCpp](https://github.com/LostRuins/koboldcpp)
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui)
* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python)
* [ctransformers](https://github.com/marella/ctransformers)
## Update 9th July 2023: GGML k-quants now available
Thanks to the work of LostRuins/concedo, it is now possible to provide 100% working GGML k-quants for models like this which have a non-standard vocab size (32,001).
k-quants have been uploaded and will work with all llama.cpp clients without any changes required.
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/WizardLM-13B-V1.1-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/WizardLM-13B-V1.1-GGML)
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/WizardLM/WizardLM-13B-V1.1)
## Prompt template: Vicuna
```
A chat between a curious user and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the user's questions.
USER: PROMPT
ASSISTANT:
```
<!-- compatibility_ggml start -->
## Compatibility
**Note:** due to this model having a non-standard vocab size of 32,001, k-quants are slightly larger than they are for other models of the same size and type.
For example, a 13B q4_K_M will be around 150MB larger. Inference speed should not be noticeably affected, and quality will be the same or higher.
### Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0`
These are guaranteed to be compatible with any UIs, tools and libraries released since late May. They may be phased out soon, as they are largely superseded by the new k-quant methods.
### New k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K`
These new quantisation methods are compatible with llama.cpp as of June 6th, commit `2d43387`.
They are now also compatible with recent releases of text-generation-webui, KoboldCpp, llama-cpp-python, ctransformers, rustformers and most others. For compatibility with other tools and libraries, please check their documentation.
## Explanation of the new k-quant methods
<details>
<summary>Click to see details</summary>
The new methods available are:
* GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
* GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
* GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
* GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
* GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
* GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type.
Refer to the Provided Files table below to see what files use which methods, and how.
</details>
<!-- compatibility_ggml end -->
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| wizardlm-13b-v1.1.ggmlv3.q2_K.bin | q2_K | 2 | 5.67 GB| 8.17 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. |
| wizardlm-13b-v1.1.ggmlv3.q3_K_L.bin | q3_K_L | 3 | 7.07 GB| 9.57 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| wizardlm-13b-v1.1.ggmlv3.q3_K_M.bin | q3_K_M | 3 | 6.46 GB| 8.96 GB | New k-quant method. Uses GGML_TYPE_Q4_K for the attention.wv, attention.wo, and feed_forward.w2 tensors, else GGML_TYPE_Q3_K |
| wizardlm-13b-v1.1.ggmlv3.q3_K_S.bin | q3_K_S | 3 | 5.80 GB| 8.30 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors |
| wizardlm-13b-v1.1.ggmlv3.q4_0.bin | q4_0 | 4 | 7.32 GB| 9.82 GB | Original quant method, 4-bit. |
| wizardlm-13b-v1.1.ggmlv3.q4_1.bin | q4_1 | 4 | 8.14 GB| 10.64 GB | Original quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
| wizardlm-13b-v1.1.ggmlv3.q4_K_M.bin | q4_K_M | 4 | 7.99 GB| 10.49 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q4_K |
| wizardlm-13b-v1.1.ggmlv3.q4_K_S.bin | q4_K_S | 4 | 7.49 GB| 9.99 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors |
| wizardlm-13b-v1.1.ggmlv3.q5_0.bin | q5_0 | 5 | 8.95 GB| 11.45 GB | Original quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
| wizardlm-13b-v1.1.ggmlv3.q5_1.bin | q5_1 | 5 | 9.76 GB| 12.26 GB | Original quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
| wizardlm-13b-v1.1.ggmlv3.q5_K_M.bin | q5_K_M | 5 | 9.33 GB| 11.83 GB | New k-quant method. Uses GGML_TYPE_Q6_K for half of the attention.wv and feed_forward.w2 tensors, else GGML_TYPE_Q5_K |
| wizardlm-13b-v1.1.ggmlv3.q5_K_S.bin | q5_K_S | 5 | 9.07 GB| 11.57 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
| wizardlm-13b-v1.1.ggmlv3.q6_K.bin | q6_K | 6 | 10.76 GB| 13.26 GB | New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors |
| wizardlm-13b-v1.1.ggmlv3.q8_0.bin | q8_0 | 8 | 13.83 GB| 16.33 GB | Original quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
## How to run in `llama.cpp`
I use the following command line; adjust for your tastes and needs:
```
./main -t 10 -ngl 32 -m wizardlm-13b-v1.1.ggmlv3.q4_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### Instruction: Write a story about llamas\n### Response:"
```
Change `-t 10` to the number of physical CPU cores you have. For example if your system has 8 cores/16 threads, use `-t 8`.
Change `-ngl 32` to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.
If you want to have a chat-style conversation, replace the `-p <PROMPT>` argument with `-i -ins`
## How to run in `text-generation-webui`
Further instructions here: [text-generation-webui/docs/llama.cpp-models.md](https://github.com/oobabooga/text-generation-webui/blob/main/docs/llama.cpp-models.md).
<!-- footer start -->
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/theblokeai)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz.
**Patreon special mentions**: RoA, Lone Striker, Gabriel Puliatti, Derek Yates, Randy H, Jonathan Leane, Eugene Pentland, Karl Bernard, Viktor Bowallius, senxiiz, Daniel P. Andersen, Pierre Kircher, Deep Realms, Cory Kujawski, Oscar Rangel, Fen Risland, Ajan Kanaga, LangChain4j, webtim, Nikolai Manek, Trenton Dambrowitz, Raven Klaugh, Kalila, Khalefa Al-Ahmad, Chris McCloskey, Luke @flexchar, Ai Maven, Dave, Asp the Wyvern, Sean Connelly, Imad Khwaja, Space Cruiser, Rainer Wilmers, subjectnull, Alps Aficionado, Willian Hasse, Fred von Graf, Artur Olbinski, Johann-Peter Hartmann, WelcomeToTheClub, Willem Michiel, Michael Levine, Iucharbius , Spiking Neurons AB, K, biorpg, John Villwock, Pyrater, Greatston Gnanesh, Mano Prime, Junyu Yang, Stephen Murray, John Detwiler, Luke Pendergrass, terasurfer , Pieter, zynix , Edmond Seymore, theTransient, Nathan LeClaire, vamX, Kevin Schuppel, Preetika Verma, ya boyyy, Alex , SuperWojo, Ghost , Joseph William Delisle, Matthew Berman, Talal Aujan, chris gileta, Illia Dulskyi.
Thank you to all my generous patrons and donaters!
<!-- footer end -->
# Original model card: WizardLM's WizardLM 13B V1.1
This is the **Full-Weight** of WizardLM-13B V1.1 model.
**Repository**: https://github.com/nlpxucan/WizardLM
**Twitter**: https://twitter.com/WizardLM_AI/status/1677282955490918401
- 🔥🔥🔥 [7/7/2023] We released **WizardLM V1.1** models. The **WizardLM-13B-V1.1** is here ([Demo_13B-V1.1](https://e8a06366ccd1c4d1.gradio.app), [Demo_13B-V1.1_bak-1](https://59da107262a25764.gradio.app), [Demo_13B-V1.1_bak-2](https://dfc5113f66739c80.gradio.app), [Full Model Weight](https://huggingface.co/WizardLM/WizardLM-13B-V1.1)). **WizardLM-7B-V1.1**, **WizardLM-30B-V1.1**, and **WizardLM-65B-V1.1** are coming soon. Please checkout the [Full Model Weights](https://huggingface.co/WizardLM) and [paper](https://arxiv.org/abs/2304.12244).
- 🔥🔥🔥 [7/7/2023] The **WizardLM-13B-V1.1** achieves **6.74** on [MT-Bench Leaderboard](https://chat.lmsys.org/?leaderboard), **86.32%** on [AlpacaEval Leaderboard](https://tatsu-lab.github.io/alpaca_eval/), and **99.3%** on [WizardLM Eval](https://github.com/nlpxucan/WizardLM/blob/main/WizardLM/data/WizardLM_testset.jsonl). (Note: MT-Bench and AlpacaEval are all self-test, will push update and request review. All tests are completed under their official settings.)
|
hvisionrc/vit-base-patch16-224-finetuned-flower | hvisionrc | "2023-07-09T17:23:27Z" | 165 | 0 | transformers | [
"transformers",
"pytorch",
"vit",
"image-classification",
"generated_from_trainer",
"dataset:imagefolder",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | image-classification | "2023-07-09T17:12:42Z" | ---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- imagefolder
model-index:
- name: vit-base-patch16-224-finetuned-flower
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# vit-base-patch16-224-finetuned-flower
This model is a fine-tuned version of [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224) on the imagefolder dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
### Framework versions
- Transformers 4.24.0
- Pytorch 2.0.1+cu118
- Datasets 2.7.1
- Tokenizers 0.13.3
|
shauryakudiyal/fine-tuned-bart | shauryakudiyal | "2023-07-09T17:16:22Z" | 178 | 2 | transformers | [
"transformers",
"pytorch",
"tf",
"jax",
"rust",
"bart",
"text2text-generation",
"summarization",
"en",
"dataset:cnn_dailymail",
"arxiv:1910.13461",
"license:mit",
"model-index",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | summarization | "2023-01-22T20:39:04Z" | ---
language:
- en
tags:
- summarization
license: mit
thumbnail: https://huggingface.co/front/thumbnails/facebook.png
datasets:
- cnn_dailymail
model-index:
- name: facebook/bart-large-cnn
results:
- task:
type: summarization
name: Summarization
dataset:
name: cnn_dailymail
type: cnn_dailymail
config: 3.0.0
split: train
metrics:
- name: ROUGE-1
type: rouge
value: 42.9486
verified: true
- name: ROUGE-2
type: rouge
value: 20.8149
verified: true
- name: ROUGE-L
type: rouge
value: 30.6186
verified: true
- name: ROUGE-LSUM
type: rouge
value: 40.0376
verified: true
- name: loss
type: loss
value: 2.529000997543335
verified: true
- name: gen_len
type: gen_len
value: 78.5866
verified: true
---
# BART (large-sized model), fine-tuned on CNN Daily Mail
BART model pre-trained on English language, and fine-tuned on [CNN Daily Mail](https://huggingface.co/datasets/cnn_dailymail). It was introduced in the paper [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://arxiv.org/abs/1910.13461) by Lewis et al. and first released in [this repository (https://github.com/pytorch/fairseq/tree/master/examples/bart).
Disclaimer: The team releasing BART did not write a model card for this model so this model card has been written by the Hugging Face team.
## Model description
BART is a transformer encoder-encoder (seq2seq) model with a bidirectional (BERT-like) encoder and an autoregressive (GPT-like) decoder. BART is pre-trained by (1) corrupting text with an arbitrary noising function, and (2) learning a model to reconstruct the original text.
BART is particularly effective when fine-tuned for text generation (e.g. summarization, translation) but also works well for comprehension tasks (e.g. text classification, question answering). This particular checkpoint has been fine-tuned on CNN Daily Mail, a large collection of text-summary pairs.
## Intended uses & limitations
You can use this model for text summarization.
### How to use
Here is how to use this model with the [pipeline API](https://huggingface.co/transformers/main_classes/pipelines.html):
```python
from transformers import pipeline
summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
ARTICLE = """ New York (CNN)When Liana Barrientos was 23 years old, she got married in Westchester County, New York.
A year later, she got married again in Westchester County, but to a different man and without divorcing her first husband.
Only 18 days after that marriage, she got hitched yet again. Then, Barrientos declared "I do" five more times, sometimes only within two weeks of each other.
In 2010, she married once more, this time in the Bronx. In an application for a marriage license, she stated it was her "first and only" marriage.
Barrientos, now 39, is facing two criminal counts of "offering a false instrument for filing in the first degree," referring to her false statements on the
2010 marriage license application, according to court documents.
Prosecutors said the marriages were part of an immigration scam.
On Friday, she pleaded not guilty at State Supreme Court in the Bronx, according to her attorney, Christopher Wright, who declined to comment further.
After leaving court, Barrientos was arrested and charged with theft of service and criminal trespass for allegedly sneaking into the New York subway through an emergency exit, said Detective
Annette Markowski, a police spokeswoman. In total, Barrientos has been married 10 times, with nine of her marriages occurring between 1999 and 2002.
All occurred either in Westchester County, Long Island, New Jersey or the Bronx. She is believed to still be married to four men, and at one time, she was married to eight men at once, prosecutors say.
Prosecutors said the immigration scam involved some of her husbands, who filed for permanent residence status shortly after the marriages.
Any divorces happened only after such filings were approved. It was unclear whether any of the men will be prosecuted.
The case was referred to the Bronx District Attorney\'s Office by Immigration and Customs Enforcement and the Department of Homeland Security\'s
Investigation Division. Seven of the men are from so-called "red-flagged" countries, including Egypt, Turkey, Georgia, Pakistan and Mali.
Her eighth husband, Rashid Rajput, was deported in 2006 to his native Pakistan after an investigation by the Joint Terrorism Task Force.
If convicted, Barrientos faces up to four years in prison. Her next court appearance is scheduled for May 18.
"""
print(summarizer(ARTICLE, max_length=130, min_length=30, do_sample=False))
>>> [{'summary_text': 'Liana Barrientos, 39, is charged with two counts of "offering a false instrument for filing in the first degree" In total, she has been married 10 times, with nine of her marriages occurring between 1999 and 2002. She is believed to still be married to four men.'}]
```
### BibTeX entry and citation info
```bibtex
@article{DBLP:journals/corr/abs-1910-13461,
author = {Mike Lewis and
Yinhan Liu and
Naman Goyal and
Marjan Ghazvininejad and
Abdelrahman Mohamed and
Omer Levy and
Veselin Stoyanov and
Luke Zettlemoyer},
title = {{BART:} Denoising Sequence-to-Sequence Pre-training for Natural Language
Generation, Translation, and Comprehension},
journal = {CoRR},
volume = {abs/1910.13461},
year = {2019},
url = {http://arxiv.org/abs/1910.13461},
eprinttype = {arXiv},
eprint = {1910.13461},
timestamp = {Thu, 31 Oct 2019 14:02:26 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-1910-13461.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
} |
hsc748NLP/GujiRoBERTa_fan | hsc748NLP | "2023-07-09T17:14:45Z" | 111 | 1 | transformers | [
"transformers",
"pytorch",
"bert",
"fill-mask",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | "2023-07-09T16:41:37Z" | ---
tags:
- generated_from_trainer
model-index:
- name: output
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# output
This model is a fine-tuned version of [/gemini/data-1/sikuroberta_vocabtxt](https://huggingface.co//gemini/data-1/sikuroberta_vocabtxt) on the None dataset.
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 192
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5.0
### Training results
### Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu117
- Datasets 2.12.0
- Tokenizers 0.13.3
|
snowkidy/stable-diffusion-xl-base-0.9 | snowkidy | "2023-07-09T17:12:11Z" | 81 | 5 | diffusers | [
"diffusers",
"safetensors",
"arxiv:2108.01073",
"arxiv:2112.10752",
"arxiv:2307.01952",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionXLPipeline",
"region:us"
] | text-to-image | "2023-07-09T16:57:52Z" | ---
license: other
extra_gated_prompt: "Copyright (c) Stability AI Ltd.
This License Agreement (as may be amended in accordance with this License Agreement, “License”), between you, or your employer or other entity (if you are entering into this agreement on behalf of your employer or other entity) (“Licensee” or “you”) and Stability AI Ltd. (“Stability AI” or “we”) applies to your use of any computer program, algorithm, source code, object code, software, models, or model weights that is made available by Stability AI under this License (“Software”) and any specifications, manuals, documentation, and other written information provided by Stability AI related to the Software (“Documentation”).
By using the Software, you agree to the terms of this License. If you do not agree to this License, then you do not have any rights to use the Software or Documentation (collectively, the “Software Products”), and you must immediately cease using the Software Products. If you are agreeing to be bound by the terms of this License on behalf of your employer or other entity, you represent and warrant to Stability AI that you have full legal authority to bind your employer or such entity to this License. If you do not have the requisite authority, you may not accept the License or access the Software Products on behalf of your employer or other entity.
1. LICENSE GRANT
a. Subject to your compliance with the Documentation and Sections 2, 3, and 5, Stability AI grants you a non-exclusive, worldwide, non-transferable, non-sublicensable, revocable, royalty free and limited license under Stability AI’s copyright interests to use, reproduce, and create derivative works of the Software solely for your non-commercial research purposes. The foregoing license is personal to you, and you may not assign, sublicense, distribute, publish, host, or otherwise make available this Software, derivative works of the Software, models or model weights associated with the Software, this License, or any other rights or obligations under this License without Stability AI’s prior written consent; any such assignment or sublicense without Stability AI’s prior written consent will be void and will automatically and immediately terminate this License. For sake of clarity, this License does not grant to you the right or ability to extend any license to the Software, derivative works of the Software, or associated models or model weights to a non-Licensee, nor does this License permit you to create a new Licensee, such as by making available a copy of this License. If you would like rights not granted by this License, you may seek permission by sending an email to legal@stability.ai.
b. You may make a reasonable number of copies of the Documentation solely for your use in connection with the license to the Software granted above.
c. The grant of rights expressly set forth in this Section 1 (License Grant) are the complete grant of rights to you in the Software Products, and no other licenses are granted, whether by waiver, estoppel, implication, equity or otherwise. Stability AI and its licensors reserve all rights not expressly granted by this License.
2. RESTRICTIONS
You will not, and will not permit, assist or cause any third party to:
a. use, modify, copy, reproduce, create derivative works of, or distribute the Software Products (or any derivative works thereof, works incorporating the Software Products, or any data produced by the Software), in whole or in part, for (i) any commercial or production purposes, (ii) military purposes or in the service of nuclear technology, (iii) purposes of surveillance, including any research or development relating to surveillance, (iv) biometric processing, (v) in any manner that infringes, misappropriates, or otherwise violates any third-party rights, or (vi) in any manner that violates any applicable law and violating any privacy or security laws, rules, regulations, directives, or governmental requirements (including the General Data Privacy Regulation (Regulation (EU) 2016/679), the California Consumer Privacy Act, and any and all laws governing the processing of biometric information), as well as all amendments and successor laws to any of the foregoing;
b. alter or remove copyright and other proprietary notices which appear on or in the Software Products;
c. utilize any equipment, device, software, or other means to circumvent or remove any security or protection used by Stability AI in connection with the Software, or to circumvent or remove any usage restrictions, or to enable functionality disabled by Stability AI; or
d. offer or impose any terms on the Software Products that alter, restrict, or are inconsistent with the terms of this License.
e. 1) violate any applicable U.S. and non-U.S. export control and trade sanctions laws (“Export Laws”); 2) directly or indirectly export, re-export, provide, or otherwise transfer Software Products: (a) to any individual, entity, or country prohibited by Export Laws; (b) to anyone on U.S. or non-U.S. government restricted parties lists; or (c) for any purpose prohibited by Export Laws, including nuclear, chemical or biological weapons, or missile technology applications; 3) use or download Software Products if you or they are: (a) located in a comprehensively sanctioned jurisdiction, (b) currently listed on any U.S. or non-U.S. restricted parties list, or (c) for any purpose prohibited by Export Laws; and (4) will not disguise your location through IP proxying or other methods.
3. ATTRIBUTION
Together with any copies of the Software Products (as well as derivative works thereof or works incorporating the Software Products) that you distribute, you must provide (i) a copy of this License, and (ii) the following attribution notice: “SDXL 0.9 is licensed under the SDXL Research License, Copyright (c) Stability AI Ltd. All Rights Reserved.”
4. DISCLAIMERS
THE SOFTWARE PRODUCTS ARE PROVIDED “AS IS” AND “WITH ALL FAULTS” WITH NO WARRANTY OF ANY KIND, EXPRESS OR IMPLIED. STABILITY AI EXPRESSLY DISCLAIMS ALL REPRESENTATIONS AND WARRANTIES, EXPRESS OR IMPLIED, WHETHER BY STATUTE, CUSTOM, USAGE OR OTHERWISE AS TO ANY MATTERS RELATED TO THE SOFTWARE PRODUCTS, INCLUDING BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE, TITLE, SATISFACTORY QUALITY, OR NON-INFRINGEMENT. STABILITY AI MAKES NO WARRANTIES OR REPRESENTATIONS THAT THE SOFTWARE PRODUCTS WILL BE ERROR FREE OR FREE OF VIRUSES OR OTHER HARMFUL COMPONENTS, OR PRODUCE ANY PARTICULAR RESULTS.
5. LIMITATION OF LIABILITY
TO THE FULLEST EXTENT PERMITTED BY LAW, IN NO EVENT WILL STABILITY AI BE LIABLE TO YOU (A) UNDER ANY THEORY OF LIABILITY, WHETHER BASED IN CONTRACT, TORT, NEGLIGENCE, STRICT LIABILITY, WARRANTY, OR OTHERWISE UNDER THIS LICENSE, OR (B) FOR ANY INDIRECT, CONSEQUENTIAL, EXEMPLARY, INCIDENTAL, PUNITIVE OR SPECIAL DAMAGES OR LOST PROFITS, EVEN IF STABILITY AI HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES. THE SOFTWARE PRODUCTS, THEIR CONSTITUENT COMPONENTS, AND ANY OUTPUT (COLLECTIVELY, “SOFTWARE MATERIALS”) ARE NOT DESIGNED OR INTENDED FOR USE IN ANY APPLICATION OR SITUATION WHERE FAILURE OR FAULT OF THE SOFTWARE MATERIALS COULD REASONABLY BE ANTICIPATED TO LEAD TO SERIOUS INJURY OF ANY PERSON, INCLUDING POTENTIAL DISCRIMINATION OR VIOLATION OF AN INDIVIDUAL’S PRIVACY RIGHTS, OR TO SEVERE PHYSICAL, PROPERTY, OR ENVIRONMENTAL DAMAGE (EACH, A “HIGH-RISK USE”). IF YOU ELECT TO USE ANY OF THE SOFTWARE MATERIALS FOR A HIGH-RISK USE, YOU DO SO AT YOUR OWN RISK. YOU AGREE TO DESIGN AND IMPLEMENT APPROPRIATE DECISION-MAKING AND RISK-MITIGATION PROCEDURES AND POLICIES IN CONNECTION WITH A HIGH-RISK USE SUCH THAT EVEN IF THERE IS A FAILURE OR FAULT IN ANY OF THE SOFTWARE MATERIALS, THE SAFETY OF PERSONS OR PROPERTY AFFECTED BY THE ACTIVITY STAYS AT A LEVEL THAT IS REASONABLE, APPROPRIATE, AND LAWFUL FOR THE FIELD OF THE HIGH-RISK USE.
6. INDEMNIFICATION
You will indemnify, defend and hold harmless Stability AI and our subsidiaries and affiliates, and each of our respective shareholders, directors, officers, employees, agents, successors, and assigns (collectively, the “Stability AI Parties”) from and against any losses, liabilities, damages, fines, penalties, and expenses (including reasonable attorneys’ fees) incurred by any Stability AI Party in connection with any claim, demand, allegation, lawsuit, proceeding, or investigation (collectively, “Claims”) arising out of or related to: (a) your access to or use of the Software Products (as well as any results or data generated from such access or use), including any High-Risk Use (defined below); (b) your violation of this License; or (c) your violation, misappropriation or infringement of any rights of another (including intellectual property or other proprietary rights and privacy rights). You will promptly notify the Stability AI Parties of any such Claims, and cooperate with Stability AI Parties in defending such Claims. You will also grant the Stability AI Parties sole control of the defense or settlement, at Stability AI’s sole option, of any Claims. This indemnity is in addition to, and not in lieu of, any other indemnities or remedies set forth in a written agreement between you and Stability AI or the other Stability AI Parties.
7. TERMINATION; SURVIVAL
a. This License will automatically terminate upon any breach by you of the terms of this License.
b. We may terminate this License, in whole or in part, at any time upon notice (including electronic) to you.
c. The following sections survive termination of this License: 2 (Restrictions), 3 (Attribution), 4 (Disclaimers), 5 (Limitation on Liability), 6 (Indemnification) 7 (Termination; Survival), 8 (Third Party Materials), 9 (Trademarks), 10 (Applicable Law; Dispute Resolution), and 11 (Miscellaneous).
8. THIRD PARTY MATERIALS
The Software Products may contain third-party software or other components (including free and open source software) (all of the foregoing, “Third Party Materials”), which are subject to the license terms of the respective third-party licensors. Your dealings or correspondence with third parties and your use of or interaction with any Third Party Materials are solely between you and the third party. Stability AI does not control or endorse, and makes no representations or warranties regarding, any Third Party Materials, and your access to and use of such Third Party Materials are at your own risk.
9. TRADEMARKS
Licensee has not been granted any trademark license as part of this License and may not use any name or mark associated with Stability AI without the prior written permission of Stability AI, except to the extent necessary to make the reference required by the “ATTRIBUTION” section of this Agreement.
10. APPLICABLE LAW; DISPUTE RESOLUTION
This License will be governed and construed under the laws of the State of California without regard to conflicts of law provisions. Any suit or proceeding arising out of or relating to this License will be brought in the federal or state courts, as applicable, in San Mateo County, California, and each party irrevocably submits to the jurisdiction and venue of such courts.
11. MISCELLANEOUS
If any provision or part of a provision of this License is unlawful, void or unenforceable, that provision or part of the provision is deemed severed from this License, and will not affect the validity and enforceability of any remaining provisions. The failure of Stability AI to exercise or enforce any right or provision of this License will not operate as a waiver of such right or provision. This License does not confer any third-party beneficiary rights upon any other person or entity. This License, together with the Documentation, contains the entire understanding between you and Stability AI regarding the subject matter of this License, and supersedes all other written or oral agreements and understandings between you and Stability AI regarding such subject matter. No change or addition to any provision of this License will be binding unless it is in writing and signed by an authorized representative of both you and Stability AI."
extra_gated_heading: "Researcher Early Access"
extra_gated_description: "SDXL 0.9 Research License Agreement"
extra_gated_button_content: "Submit application"
extra_gated_fields:
Organization: text
Nature of research: text
Personal researcher link (CV, website, github): text
Other Comments: text
I accept the above license agreement, and will use the Software non-commercially and for research purposes only: checkbox
---
# SD-XL 0.9-base Model Card
## Model
SDXL consists of a two-step pipeline for latent diffusion:
First, we use a base model to generate latents of the desired output size.
In the second step, we use a specialized high-resolution model and apply a technique called SDEdit (https://arxiv.org/abs/2108.01073, also known as "img2img")
to the latents generated in the first step, using the same prompt.
### Model Description
- **Developed by:** Stability AI
- **Model type:** Diffusion-based text-to-image generative model
- **License:** [SDXL 0.9 Research License](https://huggingface.co/stabilityai/stable-diffusion-xl-base-0.9/blob/main/LICENSE.md)
- **Model Description:** This is a model that can be used to generate and modify images based on text prompts. It is a [Latent Diffusion Model](https://arxiv.org/abs/2112.10752) that uses two fixed, pretrained text encoders ([OpenCLIP-ViT/G](https://github.com/mlfoundations/open_clip) and [CLIP-ViT/L](https://github.com/openai/CLIP/tree/main)).
- **Resources for more information:** [GitHub Repository](https://github.com/Stability-AI/generative-models) [SDXL paper on arXiv](https://arxiv.org/abs/2307.01952).
### Model Sources
<!-- Provide the basic links for the model. -->
- **Repository:** https://github.com/Stability-AI/generative-models
- **Demo [optional]:** https://clipdrop.co/stable-diffusion
### 🧨 Diffusers
Make sure to upgrade diffusers to >= 0.18.0:
```
pip install diffusers --upgrade
```
In addition make sure to install `transformers`, `safetensors`, `accelerate` as well as the invisible watermark:
```
pip install invisible_watermark transformers accelerate safetensors
```
You can use the model then as follows
```py
from diffusers import DiffusionPipeline
import torch
pipe = DiffusionPipeline.from_pretrained("stabilityai/stable-diffusion-xl-base-0.9", torch_dtype=torch.float16, use_safetensors=True, variant="fp16")
pipe.to("cuda")
# if using torch < 2.0
# pipe.enable_xformers_memory_efficient_attention()
prompt = "An astronaut riding a green horse"
images = pipe(prompt=prompt).images[0]
```
When using `torch >= 2.0`, you can improve the inference speed by 20-30% with torch.compile. Simple wrap the unet with torch compile before running the pipeline:
```py
pipe.unet = torch.compile(pipe.unet, mode="reduce-overhead", fullgraph=True)
```
If you are limited by GPU VRAM, you can enable *cpu offloading* by calling `pipe.enable_model_cpu_offload`
instead of `.to("cuda")`:
```diff
- pipe.to("cuda")
+ pipe.enable_model_cpu_offload()
```
## Uses
### Direct Use
The model is intended for research purposes only. Possible research areas and tasks include
- Generation of artworks and use in design and other artistic processes.
- Applications in educational or creative tools.
- Research on generative models.
- Safe deployment of models which have the potential to generate harmful content.
- Probing and understanding the limitations and biases of generative models.
Excluded uses are described below.
### Out-of-Scope Use
The model was not trained to be factual or true representations of people or events, and therefore using the model to generate such content is out-of-scope for the abilities of this model.
## Limitations and Bias
### Limitations
- The model does not achieve perfect photorealism
- The model cannot render legible text
- The model struggles with more difficult tasks which involve compositionality, such as rendering an image corresponding to “A red cube on top of a blue sphere”
- Faces and people in general may not be generated properly.
- The autoencoding part of the model is lossy.
### Bias
While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases.
## Evaluation
The chart above evaluates user preference for SDXL (with and without refinement) over Stable Diffusion 1.5 and 2.1.
The SDXL base model performs significantly better than the previous variants, and the model combined with the refinement module achieves the best overall performance.
|
digiplay/LuckyStrikeMix0.2Realistic | digiplay | "2023-07-09T17:07:13Z" | 311 | 1 | diffusers | [
"diffusers",
"safetensors",
"stable-diffusion",
"stable-diffusion-diffusers",
"text-to-image",
"license:other",
"autotrain_compatible",
"endpoints_compatible",
"diffusers:StableDiffusionPipeline",
"region:us"
] | text-to-image | "2023-07-08T13:03:32Z" | ---
license: other
tags:
- stable-diffusion
- stable-diffusion-diffusers
- text-to-image
- diffusers
inference: true
---
Model info :
https://civitai.com/models/13034/lucky-strike-mix
***Note: please use "realistic" keywords to make some realistic results.***
Sample image I made thru huggingface's API:
```
realistic ,MCU,(masterpiece, best quality, ultra high res:1.3), 1girl, (abstract art:1.3), half demon,
```
|
RogerB/afriberta_small-finetuned-kintweetsD | RogerB | "2023-07-09T17:05:25Z" | 103 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"xlm-roberta",
"fill-mask",
"generated_from_trainer",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | "2023-07-09T16:55:42Z" | ---
tags:
- generated_from_trainer
model-index:
- name: afriberta_small-finetuned-kintweetsD
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# afriberta_small-finetuned-kintweetsD
This model is a fine-tuned version of [castorini/afriberta_small](https://huggingface.co/castorini/afriberta_small) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.2332
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 10
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 3.6431 | 1.0 | 900 | 3.3421 |
| 3.4111 | 2.0 | 1800 | 3.2661 |
| 3.3391 | 3.0 | 2700 | 3.2382 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
turhancan97/yolov8-segment-trash-detection | turhancan97 | "2023-07-09T16:53:38Z" | 0 | 1 | null | [
"computer-vision",
"yolov8",
"segmentation",
"en",
"dataset:garythung/trashnet",
"dataset:Zesky665/TACO",
"dataset:detection-datasets/coco",
"license:mit",
"region:us"
] | null | "2023-07-09T16:42:33Z" | ---
license: mit
language:
- en
datasets:
- garythung/trashnet
- Zesky665/TACO
- detection-datasets/coco
tags:
- computer-vision
- yolov8
- segmentation
---
### Model Description
[Ultralytics:](https://github.com/ultralytics/ultralytics/) YOLOv8 in PyTorch > ONNX > CoreML > TFLite]
### Installation
```
pip install ultralytics
```
### Yolov8 Inference
```python
from ultralytics import YOLO
model = YOLO('turhancan97/yolov8-segment-trash-detection')
prediction = model.predict(image, imgsz=image_size, show=False, save=False)
``` |
NasimB/gpt2-concat-guten-rarity-iroder-est-rarity-all-5k-2p5k | NasimB | "2023-07-09T16:50:17Z" | 5 | 0 | transformers | [
"transformers",
"pytorch",
"gpt2",
"text-generation",
"generated_from_trainer",
"dataset:generator",
"license:mit",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | "2023-07-09T14:22:52Z" | ---
license: mit
tags:
- generated_from_trainer
datasets:
- generator
model-index:
- name: gpt2-concat-guten-rarity-iroder-est-rarity-all-5k-2p5k
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# gpt2-concat-guten-rarity-iroder-est-rarity-all-5k-2p5k
This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the generator dataset.
It achieves the following results on the evaluation set:
- Loss: 3.1825
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0005
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 6
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:-----:|:---------------:|
| 6.7149 | 0.3 | 500 | 5.6379 |
| 5.3626 | 0.59 | 1000 | 5.2053 |
| 5.0103 | 0.89 | 1500 | 4.9561 |
| 4.7374 | 1.18 | 2000 | 4.8042 |
| 4.5794 | 1.48 | 2500 | 4.6786 |
| 4.4756 | 1.77 | 3000 | 4.5728 |
| 4.3345 | 2.07 | 3500 | 4.4966 |
| 4.1538 | 2.36 | 4000 | 4.4468 |
| 4.1275 | 2.66 | 4500 | 4.3875 |
| 4.0815 | 2.95 | 5000 | 4.3316 |
| 3.8534 | 3.25 | 5500 | 4.3293 |
| 3.8151 | 3.54 | 6000 | 4.2939 |
| 3.8069 | 3.84 | 6500 | 4.2572 |
| 3.6706 | 4.13 | 7000 | 4.2627 |
| 3.5322 | 4.43 | 7500 | 4.2534 |
| 3.5274 | 4.73 | 8000 | 4.2397 |
| 3.4978 | 5.02 | 8500 | 4.2343 |
| 3.3402 | 5.32 | 9000 | 4.2407 |
| 3.3342 | 5.61 | 9500 | 4.2388 |
| 3.3308 | 5.91 | 10000 | 4.2382 |
### Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
|
aclodic/taxi-v3 | aclodic | "2023-07-09T16:49:05Z" | 0 | 0 | null | [
"Taxi-v3",
"q-learning",
"reinforcement-learning",
"custom-implementation",
"model-index",
"region:us"
] | reinforcement-learning | "2023-07-09T16:49:04Z" | ---
tags:
- Taxi-v3
- q-learning
- reinforcement-learning
- custom-implementation
model-index:
- name: taxi-v3
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Taxi-v3
type: Taxi-v3
metrics:
- type: mean_reward
value: 7.50 +/- 2.78
name: mean_reward
verified: false
---
# **Q-Learning** Agent playing1 **Taxi-v3**
This is a trained model of a **Q-Learning** agent playing **Taxi-v3** .
## Usage
```python
model = load_from_hub(repo_id="aclodic/taxi-v3", filename="q-learning.pkl")
# Don't forget to check if you need to add additional attributes (is_slippery=False etc)
env = gym.make(model["env_id"])
```
|
etweedy/roberta-base-squad-v2 | etweedy | "2023-07-09T16:37:08Z" | 132 | 0 | transformers | [
"transformers",
"pytorch",
"safetensors",
"roberta",
"question-answering",
"en",
"dataset:squad_v2",
"arxiv:1907.11692",
"license:apache-2.0",
"endpoints_compatible",
"region:us"
] | question-answering | "2023-07-06T03:34:13Z" | ---
datasets:
- squad_v2
language:
- en
license: apache-2.0
inference:
parameters:
handle_impossible_answer: true
---
# Model Card for etweedy/roberta-base-squad-v2
An instance of [roberta-base for QA](https://huggingface.co/roberta-base) which was fine-tuned for context-based question answering on the [SQuAD v2 dataset](https://huggingface.co/datasets/squad_v2), a dataset of English-language context-question-answer triples designed for extractive question answering training and benchmarking. Version 2 of SQuAD (Stanford Question Answering Dataset) contains the 100,000 examples from SQuAD Version 1.1, along with 50,000 additional "unanswerable" questions, i.e. questions whose answer cannot be found in the provided context.
The original RoBERTa (Robustly Optimized BERT Pretraining Approach) model was introduced in [this paper](https://arxiv.org/abs/1907.11692) and [this repository](https://github.com/facebookresearch/fairseq/tree/main/examples/roberta)
## Demonstration space
Try out inference on this model using [this app](https://huggingface.co/spaces/etweedy/roberta-squad-v2)
## Overview
**Pretrained model:** [roberta-base](https://huggingface.co/roberta-base)
**Language:** English
**Downstream-task:** Extractive QA
**Training data:** [SQuAD v2](https://huggingface.co/datasets/squad_v2) train split
**Eval data:** [SQuAD v2](https://huggingface.co/datasets/squad_v2) validation split
## How to Get Started with the Model
Initializing pipeline:
```python
from transformers import AutoModelForQuestionAnswering, AutoTokenizer, pipeline
repo_id = "etweedy/roberta-base-squad-v2"
QA_pipeline = pipeline(
task = 'question-answering',
model=repo_id,
tokenizer=repo_id,
handle_impossible_answer = True
)
```
Inference:
```python
input = {
'question': 'Who invented Twinkies?',
'context': 'Twinkies were invented on April 6, 1930, by Canadian-born baker James Alexander Dewar for the Continental Baking Company in Schiller Park, Illinois.'
}
response = QA_pipeline(**input)
```
### Training Hyperparameters
```
batch_size = 16
n_epochs = 3
learning_rate = 3e-5
base_LM_model = ["roberta-base"](https://huggingface.co/roberta-base)
max_seq_len = 384
stride=128
lr_schedule = LinearWarmup
warmup_proportion = 0.0
mixed_precision="fp16"
```
## Evaluation results
The model was evaluated on the validation split of [SQuAD v2](https://huggingface.co/datasets/squad_v2) and attained the following results:
```python
{"exact": 79.87029394424324,
"f1": 82.91251169582613,
"total": 11873,
"HasAns_exact": 77.93522267206478,
"HasAns_f1": 84.02838248389763,
"HasAns_total": 5928,
"NoAns_exact": 81.79983179142137,
"NoAns_f1": 81.79983179142137,
"NoAns_total": 5945}
```
**BibTeX base model citation:**
```bibtex
@article{DBLP:journals/corr/abs-1907-11692,
author = {Yinhan Liu and
Myle Ott and
Naman Goyal and
Jingfei Du and
Mandar Joshi and
Danqi Chen and
Omer Levy and
Mike Lewis and
Luke Zettlemoyer and
Veselin Stoyanov},
title = {RoBERTa: {A} Robustly Optimized {BERT} Pretraining Approach},
journal = {CoRR},
volume = {abs/1907.11692},
year = {2019},
url = {http://arxiv.org/abs/1907.11692},
archivePrefix = {arXiv},
eprint = {1907.11692},
timestamp = {Thu, 01 Aug 2019 08:59:33 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-1907-11692.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
```
|
hoanghoavienvo/bert-base-uncased-detect-depression-stage-one | hoanghoavienvo | "2023-07-09T16:29:45Z" | 103 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"bert",
"text-classification",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | "2023-07-09T14:53:19Z" | ---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
model-index:
- name: bert-base-uncased-detect-depression-stage-one
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# bert-base-uncased-detect-depression-stage-one
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4151
- Accuracy: 0.674
- F1: 0.7530
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
### Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:|
| 0.6185 | 1.0 | 751 | 0.5223 | 0.762 | 0.8260 |
| 0.5394 | 2.0 | 1502 | 0.5958 | 0.692 | 0.7488 |
| 0.4387 | 3.0 | 2253 | 0.6742 | 0.706 | 0.7885 |
| 0.3157 | 4.0 | 3004 | 1.1284 | 0.696 | 0.7768 |
| 0.1794 | 5.0 | 3755 | 1.4151 | 0.674 | 0.7530 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
hugfacerhaha/Reinforce-heli | hugfacerhaha | "2023-07-09T16:18:14Z" | 0 | 0 | null | [
"Pixelcopter-PLE-v0",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] | reinforcement-learning | "2023-07-09T16:18:12Z" | ---
tags:
- Pixelcopter-PLE-v0
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-heli
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: Pixelcopter-PLE-v0
type: Pixelcopter-PLE-v0
metrics:
- type: mean_reward
value: 16.60 +/- 12.43
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **Pixelcopter-PLE-v0**
This is a trained model of a **Reinforce** agent playing **Pixelcopter-PLE-v0** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
RogerB/afro-xlmr-small-finetuned-kintweetsD | RogerB | "2023-07-09T16:16:36Z" | 103 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"xlm-roberta",
"fill-mask",
"generated_from_trainer",
"license:afl-3.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | fill-mask | "2023-07-09T15:59:59Z" | ---
license: afl-3.0
tags:
- generated_from_trainer
model-index:
- name: afro-xlmr-small-finetuned-kintweetsD
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# afro-xlmr-small-finetuned-kintweetsD
This model is a fine-tuned version of [Davlan/afro-xlmr-small](https://huggingface.co/Davlan/afro-xlmr-small) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.5795
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 10
- eval_batch_size: 10
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.8179 | 1.0 | 900 | 1.6363 |
| 1.7094 | 2.0 | 1800 | 1.5927 |
| 1.6816 | 3.0 | 2700 | 1.6023 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
EleutherAI/pythia-2.8b-deduped | EleutherAI | "2023-07-09T16:06:37Z" | 11,958 | 14 | transformers | [
"transformers",
"pytorch",
"safetensors",
"gpt_neox",
"text-generation",
"causal-lm",
"pythia",
"en",
"dataset:EleutherAI/the_pile_deduplicated",
"arxiv:2304.01373",
"arxiv:2101.00027",
"arxiv:2201.07311",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | "2023-02-10T22:26:20Z" | ---
language:
- en
tags:
- pytorch
- causal-lm
- pythia
license: apache-2.0
datasets:
- EleutherAI/the_pile_deduplicated
---
The *Pythia Scaling Suite* is a collection of models developed to facilitate
interpretability research [(see paper)](https://arxiv.org/pdf/2304.01373.pdf).
It contains two sets of eight models of sizes
70M, 160M, 410M, 1B, 1.4B, 2.8B, 6.9B, and 12B. For each size, there are two
models: one trained on the Pile, and one trained on the Pile after the dataset
has been globally deduplicated. All 8 model sizes are trained on the exact
same data, in the exact same order. We also provide 154 intermediate
checkpoints per model, hosted on Hugging Face as branches.
The Pythia model suite was designed to promote scientific
research on large language models, especially interpretability research.
Despite not centering downstream performance as a design goal, we find the
models <a href="#evaluations">match or exceed</a> the performance of
similar and same-sized models, such as those in the OPT and GPT-Neo suites.
<details>
<summary style="font-weight:600">Details on previous early release and naming convention.</summary>
Previously, we released an early version of the Pythia suite to the public.
However, we decided to retrain the model suite to address a few hyperparameter
discrepancies. This model card <a href="#changelog">lists the changes</a>;
see appendix B in the Pythia paper for further discussion. We found no
difference in benchmark performance between the two Pythia versions.
The old models are
[still available](https://huggingface.co/models?other=pythia_v0), but we
suggest the retrained suite if you are just starting to use Pythia.<br>
**This is the current release.**
Please note that all models in the *Pythia* suite were renamed in January
2023. For clarity, a <a href="#naming-convention-and-parameter-count">table
comparing the old and new names</a> is provided in this model card, together
with exact parameter counts.
</details>
<br>
# Pythia-2.8B-deduped
## Model Details
- Developed by: [EleutherAI](http://eleuther.ai)
- Model type: Transformer-based Language Model
- Language: English
- Learn more: [Pythia's GitHub repository](https://github.com/EleutherAI/pythia)
for training procedure, config files, and details on how to use.
[See paper](https://arxiv.org/pdf/2304.01373.pdf) for more evals and implementation
details.
- Library: [GPT-NeoX](https://github.com/EleutherAI/gpt-neox)
- License: Apache 2.0
- Contact: to ask questions about this model, join the [EleutherAI
Discord](https://discord.gg/zBGx3azzUn), and post them in `#release-discussion`.
Please read the existing *Pythia* documentation before asking about it in the
EleutherAI Discord. For general correspondence: [contact@eleuther.
ai](mailto:contact@eleuther.ai).
<figure>
| Pythia model | Non-Embedding Params | Layers | Model Dim | Heads | Batch Size | Learning Rate | Equivalent Models |
| -----------: | -------------------: | :----: | :-------: | :---: | :--------: | :-------------------: | :--------------------: |
| 70M | 18,915,328 | 6 | 512 | 8 | 2M | 1.0 x 10<sup>-3</sup> | — |
| 160M | 85,056,000 | 12 | 768 | 12 | 2M | 6.0 x 10<sup>-4</sup> | GPT-Neo 125M, OPT-125M |
| 410M | 302,311,424 | 24 | 1024 | 16 | 2M | 3.0 x 10<sup>-4</sup> | OPT-350M |
| 1.0B | 805,736,448 | 16 | 2048 | 8 | 2M | 3.0 x 10<sup>-4</sup> | — |
| 1.4B | 1,208,602,624 | 24 | 2048 | 16 | 2M | 2.0 x 10<sup>-4</sup> | GPT-Neo 1.3B, OPT-1.3B |
| 2.8B | 2,517,652,480 | 32 | 2560 | 32 | 2M | 1.6 x 10<sup>-4</sup> | GPT-Neo 2.7B, OPT-2.7B |
| 6.9B | 6,444,163,072 | 32 | 4096 | 32 | 2M | 1.2 x 10<sup>-4</sup> | OPT-6.7B |
| 12B | 11,327,027,200 | 36 | 5120 | 40 | 2M | 1.2 x 10<sup>-4</sup> | — |
<figcaption>Engineering details for the <i>Pythia Suite</i>. Deduped and
non-deduped models of a given size have the same hyperparameters. “Equivalent”
models have <b>exactly</b> the same architecture, and the same number of
non-embedding parameters.</figcaption>
</figure>
## Uses and Limitations
### Intended Use
The primary intended use of Pythia is research on the behavior, functionality,
and limitations of large language models. This suite is intended to provide
a controlled setting for performing scientific experiments. We also provide
154 checkpoints per model: initial `step0`, 10 log-spaced checkpoints
`step{1,2,4...512}`, and 143 evenly-spaced checkpoints from `step1000` to
`step143000`. These checkpoints are hosted on Hugging Face as branches. Note
that branch `143000` corresponds exactly to the model checkpoint on the `main`
branch of each model.
You may also further fine-tune and adapt Pythia-2.8B-deduped for deployment,
as long as your use is in accordance with the Apache 2.0 license. Pythia
models work with the Hugging Face [Transformers
Library](https://huggingface.co/docs/transformers/index). If you decide to use
pre-trained Pythia-2.8B-deduped as a basis for your fine-tuned model, please
conduct your own risk and bias assessment.
### Out-of-scope use
The Pythia Suite is **not** intended for deployment. It is not a in itself
a product and cannot be used for human-facing interactions. For example,
the model may generate harmful or offensive text. Please evaluate the risks
associated with your particular use case.
Pythia models are English-language only, and are not suitable for translation
or generating text in other languages.
Pythia-2.8B-deduped has not been fine-tuned for downstream contexts in which
language models are commonly deployed, such as writing genre prose,
or commercial chatbots. This means Pythia-2.8B-deduped will **not**
respond to a given prompt the way a product like ChatGPT does. This is because,
unlike this model, ChatGPT was fine-tuned using methods such as Reinforcement
Learning from Human Feedback (RLHF) to better “follow” human instructions.
### Limitations and biases
The core functionality of a large language model is to take a string of text
and predict the next token. The token used by the model need not produce the
most “accurate” text. Never rely on Pythia-2.8B-deduped to produce factually accurate
output.
This model was trained on [the Pile](https://pile.eleuther.ai/), a dataset
known to contain profanity and texts that are lewd or otherwise offensive.
See [Section 6 of the Pile paper](https://arxiv.org/abs/2101.00027) for a
discussion of documented biases with regards to gender, religion, and race.
Pythia-2.8B-deduped may produce socially unacceptable or undesirable text, *even if*
the prompt itself does not include anything explicitly offensive.
If you plan on using text generated through, for example, the Hosted Inference
API, we recommend having a human curate the outputs of this language model
before presenting it to other people. Please inform your audience that the
text was generated by Pythia-2.8B-deduped.
### Quickstart
Pythia models can be loaded and used via the following code, demonstrated here
for the third `pythia-70m-deduped` checkpoint:
```python
from transformers import GPTNeoXForCausalLM, AutoTokenizer
model = GPTNeoXForCausalLM.from_pretrained(
"EleutherAI/pythia-70m-deduped",
revision="step3000",
cache_dir="./pythia-70m-deduped/step3000",
)
tokenizer = AutoTokenizer.from_pretrained(
"EleutherAI/pythia-70m-deduped",
revision="step3000",
cache_dir="./pythia-70m-deduped/step3000",
)
inputs = tokenizer("Hello, I am", return_tensors="pt")
tokens = model.generate(**inputs)
tokenizer.decode(tokens[0])
```
Revision/branch `step143000` corresponds exactly to the model checkpoint on
the `main` branch of each model.<br>
For more information on how to use all Pythia models, see [documentation on
GitHub](https://github.com/EleutherAI/pythia).
## Training
### Training data
Pythia-2.8B-deduped was trained on the Pile **after the dataset has been globally
deduplicated**.<br>
[The Pile](https://pile.eleuther.ai/) is a 825GiB general-purpose dataset in
English. It was created by EleutherAI specifically for training large language
models. It contains texts from 22 diverse sources, roughly broken down into
five categories: academic writing (e.g. arXiv), internet (e.g. CommonCrawl),
prose (e.g. Project Gutenberg), dialogue (e.g. YouTube subtitles), and
miscellaneous (e.g. GitHub, Enron Emails). See [the Pile
paper](https://arxiv.org/abs/2101.00027) for a breakdown of all data sources,
methodology, and a discussion of ethical implications. Consult [the
datasheet](https://arxiv.org/abs/2201.07311) for more detailed documentation
about the Pile and its component datasets. The Pile can be downloaded from
the [official website](https://pile.eleuther.ai/), or from a [community
mirror](https://the-eye.eu/public/AI/pile/).
### Training procedure
All models were trained on the exact same data, in the exact same order. Each
model saw 299,892,736,000 tokens during training, and 143 checkpoints for each
model are saved every 2,097,152,000 tokens, spaced evenly throughout training,
from `step1000` to `step143000` (which is the same as `main`). In addition, we
also provide frequent early checkpoints: `step0` and `step{1,2,4...512}`.
This corresponds to training for just under 1 epoch on the Pile for
non-deduplicated models, and about 1.5 epochs on the deduplicated Pile.
All *Pythia* models trained for 143000 steps at a batch size
of 2M (2,097,152 tokens).<br>
See [GitHub](https://github.com/EleutherAI/pythia) for more details on training
procedure, including [how to reproduce
it](https://github.com/EleutherAI/pythia/blob/main/README.md#reproducing-training).<br>
Pythia uses the same tokenizer as [GPT-NeoX-
20B](https://huggingface.co/EleutherAI/gpt-neox-20b).
## Evaluations
All 16 *Pythia* models were evaluated using the [LM Evaluation
Harness](https://github.com/EleutherAI/lm-evaluation-harness). You can access
the results by model and step at `results/json/*` in the [GitHub
repository](https://github.com/EleutherAI/pythia/tree/main/results/json/).<br>
Expand the sections below to see plots of evaluation results for all
Pythia and Pythia-deduped models compared with OPT and BLOOM.
<details>
<summary>LAMBADA – OpenAI</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/lambada_openai_v1.png" style="width:auto"/>
</details>
<details>
<summary>Physical Interaction: Question Answering (PIQA)</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/piqa_v1.png" style="width:auto"/>
</details>
<details>
<summary>WinoGrande</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/winogrande_v1.png" style="width:auto"/>
</details>
<details>
<summary>AI2 Reasoning Challenge—Easy Set</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/arc_easy_v1.png" style="width:auto"/>
</details>
<details>
<summary>SciQ</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/sciq_v1.png" style="width:auto"/>
</details>
## Changelog
This section compares differences between previously released
[Pythia v0](https://huggingface.co/models?other=pythia_v0) and the current
models. See Appendix B of the Pythia paper for further discussion of these
changes and the motivation behind them. We found that retraining Pythia had no
impact on benchmark performance.
- All model sizes are now trained with uniform batch size of 2M tokens.
Previously, the models of size 160M, 410M, and 1.4B parameters were trained
with batch sizes of 4M tokens.
- We added checkpoints at initialization (step 0) and steps {1,2,4,8,16,32,64,
128,256,512} in addition to every 1000 training steps.
- Flash Attention was used in the new retrained suite.
- We remedied a minor inconsistency that existed in the original suite: all
models of size 2.8B parameters or smaller had a learning rate (LR) schedule
which decayed to a minimum LR of 10% the starting LR rate, but the 6.9B and
12B models all used an LR schedule which decayed to a minimum LR of 0. In
the redone training runs, we rectified this inconsistency: all models now were
trained with LR decaying to a minimum of 0.1× their maximum LR.
### Naming convention and parameter count
*Pythia* models were renamed in January 2023. It is possible that the old
naming convention still persists in some documentation by accident. The
current naming convention (70M, 160M, etc.) is based on total parameter count.
<figure style="width:32em">
| current Pythia suffix | old suffix | total params | non-embedding params |
| --------------------: | ---------: | -------------: | -------------------: |
| 70M | 19M | 70,426,624 | 18,915,328 |
| 160M | 125M | 162,322,944 | 85,056,000 |
| 410M | 350M | 405,334,016 | 302,311,424 |
| 1B | 800M | 1,011,781,632 | 805,736,448 |
| 1.4B | 1.3B | 1,414,647,808 | 1,208,602,624 |
| 2.8B | 2.7B | 2,775,208,960 | 2,517,652,480 |
| 6.9B | 6.7B | 6,857,302,016 | 6,444,163,072 |
| 12B | 13B | 11,846,072,320 | 11,327,027,200 |
</figure> |
EleutherAI/pythia-410m-deduped | EleutherAI | "2023-07-09T16:05:38Z" | 21,119 | 20 | transformers | [
"transformers",
"pytorch",
"safetensors",
"gpt_neox",
"text-generation",
"causal-lm",
"pythia",
"en",
"dataset:EleutherAI/the_pile_deduplicated",
"arxiv:2304.01373",
"arxiv:2101.00027",
"arxiv:2201.07311",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | "2023-02-13T21:27:47Z" | ---
language:
- en
tags:
- pytorch
- causal-lm
- pythia
license: apache-2.0
datasets:
- EleutherAI/the_pile_deduplicated
---
The *Pythia Scaling Suite* is a collection of models developed to facilitate
interpretability research [(see paper)](https://arxiv.org/pdf/2304.01373.pdf).
It contains two sets of eight models of sizes
70M, 160M, 410M, 1B, 1.4B, 2.8B, 6.9B, and 12B. For each size, there are two
models: one trained on the Pile, and one trained on the Pile after the dataset
has been globally deduplicated. All 8 model sizes are trained on the exact
same data, in the exact same order. We also provide 154 intermediate
checkpoints per model, hosted on Hugging Face as branches.
The Pythia model suite was designed to promote scientific
research on large language models, especially interpretability research.
Despite not centering downstream performance as a design goal, we find the
models <a href="#evaluations">match or exceed</a> the performance of
similar and same-sized models, such as those in the OPT and GPT-Neo suites.
<details>
<summary style="font-weight:600">Details on previous early release and naming convention.</summary>
Previously, we released an early version of the Pythia suite to the public.
However, we decided to retrain the model suite to address a few hyperparameter
discrepancies. This model card <a href="#changelog">lists the changes</a>;
see appendix B in the Pythia paper for further discussion. We found no
difference in benchmark performance between the two Pythia versions.
The old models are
[still available](https://huggingface.co/models?other=pythia_v0), but we
suggest the retrained suite if you are just starting to use Pythia.<br>
**This is the current release.**
Please note that all models in the *Pythia* suite were renamed in January
2023. For clarity, a <a href="#naming-convention-and-parameter-count">table
comparing the old and new names</a> is provided in this model card, together
with exact parameter counts.
</details>
<br>
# Pythia-410M-deduped
## Model Details
- Developed by: [EleutherAI](http://eleuther.ai)
- Model type: Transformer-based Language Model
- Language: English
- Learn more: [Pythia's GitHub repository](https://github.com/EleutherAI/pythia)
for training procedure, config files, and details on how to use.
[See paper](https://arxiv.org/pdf/2304.01373.pdf) for more evals and implementation
details.
- Library: [GPT-NeoX](https://github.com/EleutherAI/gpt-neox)
- License: Apache 2.0
- Contact: to ask questions about this model, join the [EleutherAI
Discord](https://discord.gg/zBGx3azzUn), and post them in `#release-discussion`.
Please read the existing *Pythia* documentation before asking about it in the
EleutherAI Discord. For general correspondence: [contact@eleuther.
ai](mailto:contact@eleuther.ai).
<figure>
| Pythia model | Non-Embedding Params | Layers | Model Dim | Heads | Batch Size | Learning Rate | Equivalent Models |
| -----------: | -------------------: | :----: | :-------: | :---: | :--------: | :-------------------: | :--------------------: |
| 70M | 18,915,328 | 6 | 512 | 8 | 2M | 1.0 x 10<sup>-3</sup> | — |
| 160M | 85,056,000 | 12 | 768 | 12 | 2M | 6.0 x 10<sup>-4</sup> | GPT-Neo 125M, OPT-125M |
| 410M | 302,311,424 | 24 | 1024 | 16 | 2M | 3.0 x 10<sup>-4</sup> | OPT-350M |
| 1.0B | 805,736,448 | 16 | 2048 | 8 | 2M | 3.0 x 10<sup>-4</sup> | — |
| 1.4B | 1,208,602,624 | 24 | 2048 | 16 | 2M | 2.0 x 10<sup>-4</sup> | GPT-Neo 1.3B, OPT-1.3B |
| 2.8B | 2,517,652,480 | 32 | 2560 | 32 | 2M | 1.6 x 10<sup>-4</sup> | GPT-Neo 2.7B, OPT-2.7B |
| 6.9B | 6,444,163,072 | 32 | 4096 | 32 | 2M | 1.2 x 10<sup>-4</sup> | OPT-6.7B |
| 12B | 11,327,027,200 | 36 | 5120 | 40 | 2M | 1.2 x 10<sup>-4</sup> | — |
<figcaption>Engineering details for the <i>Pythia Suite</i>. Deduped and
non-deduped models of a given size have the same hyperparameters. “Equivalent”
models have <b>exactly</b> the same architecture, and the same number of
non-embedding parameters.</figcaption>
</figure>
## Uses and Limitations
### Intended Use
The primary intended use of Pythia is research on the behavior, functionality,
and limitations of large language models. This suite is intended to provide
a controlled setting for performing scientific experiments. We also provide
154 checkpoints per model: initial `step0`, 10 log-spaced checkpoints
`step{1,2,4...512}`, and 143 evenly-spaced checkpoints from `step1000` to
`step143000`. These checkpoints are hosted on Hugging Face as branches. Note
that branch `143000` corresponds exactly to the model checkpoint on the `main`
branch of each model.
You may also further fine-tune and adapt Pythia-410M-deduped for deployment,
as long as your use is in accordance with the Apache 2.0 license. Pythia
models work with the Hugging Face [Transformers
Library](https://huggingface.co/docs/transformers/index). If you decide to use
pre-trained Pythia-410M-deduped as a basis for your fine-tuned model, please
conduct your own risk and bias assessment.
### Out-of-scope use
The Pythia Suite is **not** intended for deployment. It is not a in itself
a product and cannot be used for human-facing interactions. For example,
the model may generate harmful or offensive text. Please evaluate the risks
associated with your particular use case.
Pythia models are English-language only, and are not suitable for translation
or generating text in other languages.
Pythia-410M-deduped has not been fine-tuned for downstream contexts in which
language models are commonly deployed, such as writing genre prose,
or commercial chatbots. This means XNPythia-410M-dedupedAME will **not**
respond to a given prompt the way a product like ChatGPT does. This is because,
unlike this model, ChatGPT was fine-tuned using methods such as Reinforcement
Learning from Human Feedback (RLHF) to better “follow” human instructions.
### Limitations and biases
The core functionality of a large language model is to take a string of text
and predict the next token. The token used by the model need not produce the
most “accurate” text. Never rely on Pythia-410M-deduped to produce factually accurate
output.
This model was trained on [the Pile](https://pile.eleuther.ai/), a dataset
known to contain profanity and texts that are lewd or otherwise offensive.
See [Section 6 of the Pile paper](https://arxiv.org/abs/2101.00027) for a
discussion of documented biases with regards to gender, religion, and race.
Pythia-410M-deduped may produce socially unacceptable or undesirable text, *even if*
the prompt itself does not include anything explicitly offensive.
If you plan on using text generated through, for example, the Hosted Inference
API, we recommend having a human curate the outputs of this language model
before presenting it to other people. Please inform your audience that the
text was generated by Pythia-410M-deduped.
### Quickstart
Pythia models can be loaded and used via the following code, demonstrated here
for the third `pythia-70m-deduped` checkpoint:
```python
from transformers import GPTNeoXForCausalLM, AutoTokenizer
model = GPTNeoXForCausalLM.from_pretrained(
"EleutherAI/pythia-70m-deduped",
revision="step3000",
cache_dir="./pythia-70m-deduped/step3000",
)
tokenizer = AutoTokenizer.from_pretrained(
"EleutherAI/pythia-70m-deduped",
revision="step3000",
cache_dir="./pythia-70m-deduped/step3000",
)
inputs = tokenizer("Hello, I am", return_tensors="pt")
tokens = model.generate(**inputs)
tokenizer.decode(tokens[0])
```
Revision/branch `step143000` corresponds exactly to the model checkpoint on
the `main` branch of each model.<br>
For more information on how to use all Pythia models, see [documentation on
GitHub](https://github.com/EleutherAI/pythia).
## Training
### Training data
Pythia-410M-deduped was trained on the Pile **after the dataset has been globally
deduplicated**.<br>
[The Pile](https://pile.eleuther.ai/) is a 825GiB general-purpose dataset in
English. It was created by EleutherAI specifically for training large language
models. It contains texts from 22 diverse sources, roughly broken down into
five categories: academic writing (e.g. arXiv), internet (e.g. CommonCrawl),
prose (e.g. Project Gutenberg), dialogue (e.g. YouTube subtitles), and
miscellaneous (e.g. GitHub, Enron Emails). See [the Pile
paper](https://arxiv.org/abs/2101.00027) for a breakdown of all data sources,
methodology, and a discussion of ethical implications. Consult [the
datasheet](https://arxiv.org/abs/2201.07311) for more detailed documentation
about the Pile and its component datasets. The Pile can be downloaded from
the [official website](https://pile.eleuther.ai/), or from a [community
mirror](https://the-eye.eu/public/AI/pile/).
### Training procedure
All models were trained on the exact same data, in the exact same order. Each
model saw 299,892,736,000 tokens during training, and 143 checkpoints for each
model are saved every 2,097,152,000 tokens, spaced evenly throughout training,
from `step1000` to `step143000` (which is the same as `main`). In addition, we
also provide frequent early checkpoints: `step0` and `step{1,2,4...512}`.
This corresponds to training for just under 1 epoch on the Pile for
non-deduplicated models, and about 1.5 epochs on the deduplicated Pile.
All *Pythia* models trained for 143000 steps at a batch size
of 2M (2,097,152 tokens).<br>
See [GitHub](https://github.com/EleutherAI/pythia) for more details on training
procedure, including [how to reproduce
it](https://github.com/EleutherAI/pythia/blob/main/README.md#reproducing-training).<br>
Pythia uses the same tokenizer as [GPT-NeoX-
20B](https://huggingface.co/EleutherAI/gpt-neox-20b).
## Evaluations
All 16 *Pythia* models were evaluated using the [LM Evaluation
Harness](https://github.com/EleutherAI/lm-evaluation-harness). You can access
the results by model and step at `results/json/*` in the [GitHub
repository](https://github.com/EleutherAI/pythia/tree/main/results/json/).<br>
Expand the sections below to see plots of evaluation results for all
Pythia and Pythia-deduped models compared with OPT and BLOOM.
<details>
<summary>LAMBADA – OpenAI</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/lambada_openai_v1.png" style="width:auto"/>
</details>
<details>
<summary>Physical Interaction: Question Answering (PIQA)</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/piqa_v1.png" style="width:auto"/>
</details>
<details>
<summary>WinoGrande</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/winogrande_v1.png" style="width:auto"/>
</details>
<details>
<summary>AI2 Reasoning Challenge—Easy Set</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/arc_easy_v1.png" style="width:auto"/>
</details>
<details>
<summary>SciQ</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/sciq_v1.png" style="width:auto"/>
</details>
## Changelog
This section compares differences between previously released
[Pythia v0](https://huggingface.co/models?other=pythia_v0) and the current
models. See Appendix B of the Pythia paper for further discussion of these
changes and the motivation behind them. We found that retraining Pythia had no
impact on benchmark performance.
- All model sizes are now trained with uniform batch size of 2M tokens.
Previously, the models of size 160M, 410M, and 1.4B parameters were trained
with batch sizes of 4M tokens.
- We added checkpoints at initialization (step 0) and steps {1,2,4,8,16,32,64,
128,256,512} in addition to every 1000 training steps.
- Flash Attention was used in the new retrained suite.
- We remedied a minor inconsistency that existed in the original suite: all
models of size 2.8B parameters or smaller had a learning rate (LR) schedule
which decayed to a minimum LR of 10% the starting LR rate, but the 6.9B and
12B models all used an LR schedule which decayed to a minimum LR of 0. In
the redone training runs, we rectified this inconsistency: all models now were
trained with LR decaying to a minimum of 0.1× their maximum LR.
### Naming convention and parameter count
*Pythia* models were renamed in January 2023. It is possible that the old
naming convention still persists in some documentation by accident. The
current naming convention (70M, 160M, etc.) is based on total parameter count.
<figure style="width:32em">
| current Pythia suffix | old suffix | total params | non-embedding params |
| --------------------: | ---------: | -------------: | -------------------: |
| 70M | 19M | 70,426,624 | 18,915,328 |
| 160M | 125M | 162,322,944 | 85,056,000 |
| 410M | 350M | 405,334,016 | 302,311,424 |
| 1B | 800M | 1,011,781,632 | 805,736,448 |
| 1.4B | 1.3B | 1,414,647,808 | 1,208,602,624 |
| 2.8B | 2.7B | 2,775,208,960 | 2,517,652,480 |
| 6.9B | 6.7B | 6,857,302,016 | 6,444,163,072 |
| 12B | 13B | 11,846,072,320 | 11,327,027,200 |
</figure> |
EleutherAI/pythia-160m-deduped | EleutherAI | "2023-07-09T16:04:57Z" | 43,492 | 3 | transformers | [
"transformers",
"pytorch",
"safetensors",
"gpt_neox",
"text-generation",
"causal-lm",
"pythia",
"en",
"dataset:EleutherAI/the_pile_deduplicated",
"arxiv:2304.01373",
"arxiv:2101.00027",
"arxiv:2201.07311",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | "2023-02-08T21:50:19Z" | ---
language:
- en
tags:
- pytorch
- causal-lm
- pythia
license: apache-2.0
datasets:
- EleutherAI/the_pile_deduplicated
---
The *Pythia Scaling Suite* is a collection of models developed to facilitate
interpretability research [(see paper)](https://arxiv.org/pdf/2304.01373.pdf).
It contains two sets of eight models of sizes
70M, 160M, 410M, 1B, 1.4B, 2.8B, 6.9B, and 12B. For each size, there are two
models: one trained on the Pile, and one trained on the Pile after the dataset
has been globally deduplicated. All 8 model sizes are trained on the exact
same data, in the exact same order. We also provide 154 intermediate
checkpoints per model, hosted on Hugging Face as branches.
The Pythia model suite was designed to promote scientific
research on large language models, especially interpretability research.
Despite not centering downstream performance as a design goal, we find the
models <a href="#evaluations">match or exceed</a> the performance of
similar and same-sized models, such as those in the OPT and GPT-Neo suites.
<details>
<summary style="font-weight:600">Details on previous early release and naming convention.</summary>
Previously, we released an early version of the Pythia suite to the public.
However, we decided to retrain the model suite to address a few hyperparameter
discrepancies. This model card <a href="#changelog">lists the changes</a>;
see appendix B in the Pythia paper for further discussion. We found no
difference in benchmark performance between the two Pythia versions.
The old models are
[still available](https://huggingface.co/models?other=pythia_v0), but we
suggest the retrained suite if you are just starting to use Pythia.<br>
**This is the current release.**
Please note that all models in the *Pythia* suite were renamed in January
2023. For clarity, a <a href="#naming-convention-and-parameter-count">table
comparing the old and new names</a> is provided in this model card, together
with exact parameter counts.
</details>
<br>
# Pythia-160M-deduped
## Model Details
- Developed by: [EleutherAI](http://eleuther.ai)
- Model type: Transformer-based Language Model
- Language: English
- Learn more: [Pythia's GitHub repository](https://github.com/EleutherAI/pythia)
for training procedure, config files, and details on how to use.
[See paper](https://arxiv.org/pdf/2304.01373.pdf) for more evals and implementation
details.
- Library: [GPT-NeoX](https://github.com/EleutherAI/gpt-neox)
- License: Apache 2.0
- Contact: to ask questions about this model, join the [EleutherAI
Discord](https://discord.gg/zBGx3azzUn), and post them in `#release-discussion`.
Please read the existing *Pythia* documentation before asking about it in the
EleutherAI Discord. For general correspondence: [contact@eleuther.
ai](mailto:contact@eleuther.ai).
<figure>
| Pythia model | Non-Embedding Params | Layers | Model Dim | Heads | Batch Size | Learning Rate | Equivalent Models |
| -----------: | -------------------: | :----: | :-------: | :---: | :--------: | :-------------------: | :--------------------: |
| 70M | 18,915,328 | 6 | 512 | 8 | 2M | 1.0 x 10<sup>-3</sup> | — |
| 160M | 85,056,000 | 12 | 768 | 12 | 2M | 6.0 x 10<sup>-4</sup> | GPT-Neo 125M, OPT-125M |
| 410M | 302,311,424 | 24 | 1024 | 16 | 2M | 3.0 x 10<sup>-4</sup> | OPT-350M |
| 1.0B | 805,736,448 | 16 | 2048 | 8 | 2M | 3.0 x 10<sup>-4</sup> | — |
| 1.4B | 1,208,602,624 | 24 | 2048 | 16 | 2M | 2.0 x 10<sup>-4</sup> | GPT-Neo 1.3B, OPT-1.3B |
| 2.8B | 2,517,652,480 | 32 | 2560 | 32 | 2M | 1.6 x 10<sup>-4</sup> | GPT-Neo 2.7B, OPT-2.7B |
| 6.9B | 6,444,163,072 | 32 | 4096 | 32 | 2M | 1.2 x 10<sup>-4</sup> | OPT-6.7B |
| 12B | 11,327,027,200 | 36 | 5120 | 40 | 2M | 1.2 x 10<sup>-4</sup> | — |
<figcaption>Engineering details for the <i>Pythia Suite</i>. Deduped and
non-deduped models of a given size have the same hyperparameters. “Equivalent”
models have <b>exactly</b> the same architecture, and the same number of
non-embedding parameters.</figcaption>
</figure>
## Uses and Limitations
### Intended Use
The primary intended use of Pythia is research on the behavior, functionality,
and limitations of large language models. This suite is intended to provide
a controlled setting for performing scientific experiments. We also provide
154 checkpoints per model: initial `step0`, 10 log-spaced checkpoints
`step{1,2,4...512}`, and 143 evenly-spaced checkpoints from `step1000` to
`step143000`. These checkpoints are hosted on Hugging Face as branches. Note
that branch `143000` corresponds exactly to the model checkpoint on the `main`
branch of each model.
You may also further fine-tune and adapt Pythia-160M-deduped for deployment,
as long as your use is in accordance with the Apache 2.0 license. Pythia
models work with the Hugging Face [Transformers
Library](https://huggingface.co/docs/transformers/index). If you decide to use
pre-trained Pythia-160M-deduped as a basis for your fine-tuned model, please
conduct your own risk and bias assessment.
### Out-of-scope use
The Pythia Suite is **not** intended for deployment. It is not a in itself
a product and cannot be used for human-facing interactions. For example,
the model may generate harmful or offensive text. Please evaluate the risks
associated with your particular use case.
Pythia models are English-language only, and are not suitable for translation
or generating text in other languages.
Pythia-160M-deduped has not been fine-tuned for downstream contexts in which
language models are commonly deployed, such as writing genre prose,
or commercial chatbots. This means Pythia-160M-deduped will **not**
respond to a given prompt the way a product like ChatGPT does. This is because,
unlike this model, ChatGPT was fine-tuned using methods such as Reinforcement
Learning from Human Feedback (RLHF) to better “follow” human instructions.
### Limitations and biases
The core functionality of a large language model is to take a string of text
and predict the next token. The token used by the model need not produce the
most “accurate” text. Never rely on Pythia-160M-deduped to produce factually accurate
output.
This model was trained on [the Pile](https://pile.eleuther.ai/), a dataset
known to contain profanity and texts that are lewd or otherwise offensive.
See [Section 6 of the Pile paper](https://arxiv.org/abs/2101.00027) for a
discussion of documented biases with regards to gender, religion, and race.
Pythia-160M-deduped may produce socially unacceptable or undesirable text, *even if*
the prompt itself does not include anything explicitly offensive.
If you plan on using text generated through, for example, the Hosted Inference
API, we recommend having a human curate the outputs of this language model
before presenting it to other people. Please inform your audience that the
text was generated by Pythia-160M-deduped.
### Quickstart
Pythia models can be loaded and used via the following code, demonstrated here
for the third `pythia-70m-deduped` checkpoint:
```python
from transformers import GPTNeoXForCausalLM, AutoTokenizer
model = GPTNeoXForCausalLM.from_pretrained(
"EleutherAI/pythia-70m-deduped",
revision="step3000",
cache_dir="./pythia-70m-deduped/step3000",
)
tokenizer = AutoTokenizer.from_pretrained(
"EleutherAI/pythia-70m-deduped",
revision="step3000",
cache_dir="./pythia-70m-deduped/step3000",
)
inputs = tokenizer("Hello, I am", return_tensors="pt")
tokens = model.generate(**inputs)
tokenizer.decode(tokens[0])
```
Revision/branch `step143000` corresponds exactly to the model checkpoint on
the `main` branch of each model.<br>
For more information on how to use all Pythia models, see [documentation on
GitHub](https://github.com/EleutherAI/pythia).
## Training
### Training data
Pythia-160M-deduped was trained on the Pile **after the dataset has been globally
deduplicated**.<br>
[The Pile](https://pile.eleuther.ai/) is a 825GiB general-purpose dataset in
English. It was created by EleutherAI specifically for training large language
models. It contains texts from 22 diverse sources, roughly broken down into
five categories: academic writing (e.g. arXiv), internet (e.g. CommonCrawl),
prose (e.g. Project Gutenberg), dialogue (e.g. YouTube subtitles), and
miscellaneous (e.g. GitHub, Enron Emails). See [the Pile
paper](https://arxiv.org/abs/2101.00027) for a breakdown of all data sources,
methodology, and a discussion of ethical implications. Consult [the
datasheet](https://arxiv.org/abs/2201.07311) for more detailed documentation
about the Pile and its component datasets. The Pile can be downloaded from
the [official website](https://pile.eleuther.ai/), or from a [community
mirror](https://the-eye.eu/public/AI/pile/).
### Training procedure
All models were trained on the exact same data, in the exact same order. Each
model saw 299,892,736,000 tokens during training, and 143 checkpoints for each
model are saved every 2,097,152,000 tokens, spaced evenly throughout training,
from `step1000` to `step143000` (which is the same as `main`). In addition, we
also provide frequent early checkpoints: `step0` and `step{1,2,4...512}`.
This corresponds to training for just under 1 epoch on the Pile for
non-deduplicated models, and about 1.5 epochs on the deduplicated Pile.
All *Pythia* models trained for 143000 steps at a batch size
of 2M (2,097,152 tokens).<br>
See [GitHub](https://github.com/EleutherAI/pythia) for more details on training
procedure, including [how to reproduce
it](https://github.com/EleutherAI/pythia/blob/main/README.md#reproducing-training).<br>
Pythia uses the same tokenizer as [GPT-NeoX-
20B](https://huggingface.co/EleutherAI/gpt-neox-20b).
## Evaluations
All 16 *Pythia* models were evaluated using the [LM Evaluation
Harness](https://github.com/EleutherAI/lm-evaluation-harness). You can access
the results by model and step at `results/json/*` in the [GitHub
repository](https://github.com/EleutherAI/pythia/tree/main/results/json/).<br>
Expand the sections below to see plots of evaluation results for all
Pythia and Pythia-deduped models compared with OPT and BLOOM.
<details>
<summary>LAMBADA – OpenAI</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/lambada_openai_v1.png" style="width:auto"/>
</details>
<details>
<summary>Physical Interaction: Question Answering (PIQA)</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/piqa_v1.png" style="width:auto"/>
</details>
<details>
<summary>WinoGrande</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/winogrande_v1.png" style="width:auto"/>
</details>
<details>
<summary>AI2 Reasoning Challenge—Easy Set</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/arc_easy_v1.png" style="width:auto"/>
</details>
<details>
<summary>SciQ</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/sciq_v1.png" style="width:auto"/>
</details>
## Changelog
This section compares differences between previously released
[Pythia v0](https://huggingface.co/models?other=pythia_v0) and the current
models. See Appendix B of the Pythia paper for further discussion of these
changes and the motivation behind them. We found that retraining Pythia had no
impact on benchmark performance.
- All model sizes are now trained with uniform batch size of 2M tokens.
Previously, the models of size 160M, 410M, and 1.4B parameters were trained
with batch sizes of 4M tokens.
- We added checkpoints at initialization (step 0) and steps {1,2,4,8,16,32,64,
128,256,512} in addition to every 1000 training steps.
- Flash Attention was used in the new retrained suite.
- We remedied a minor inconsistency that existed in the original suite: all
models of size 2.8B parameters or smaller had a learning rate (LR) schedule
which decayed to a minimum LR of 10% the starting LR rate, but the 6.9B and
12B models all used an LR schedule which decayed to a minimum LR of 0. In
the redone training runs, we rectified this inconsistency: all models now were
trained with LR decaying to a minimum of 0.1× their maximum LR.
### Naming convention and parameter count
*Pythia* models were renamed in January 2023. It is possible that the old
naming convention still persists in some documentation by accident. The
current naming convention (70M, 160M, etc.) is based on total parameter count.
<figure style="width:32em">
| current Pythia suffix | old suffix | total params | non-embedding params |
| --------------------: | ---------: | -------------: | -------------------: |
| 70M | 19M | 70,426,624 | 18,915,328 |
| 160M | 125M | 162,322,944 | 85,056,000 |
| 410M | 350M | 405,334,016 | 302,311,424 |
| 1B | 800M | 1,011,781,632 | 805,736,448 |
| 1.4B | 1.3B | 1,414,647,808 | 1,208,602,624 |
| 2.8B | 2.7B | 2,775,208,960 | 2,517,652,480 |
| 6.9B | 6.7B | 6,857,302,016 | 6,444,163,072 |
| 12B | 13B | 11,846,072,320 | 11,327,027,200 |
</figure> |
EleutherAI/pythia-1.4b-deduped-v0 | EleutherAI | "2023-07-09T16:02:25Z" | 124,121 | 5 | transformers | [
"transformers",
"pytorch",
"safetensors",
"gpt_neox",
"text-generation",
"causal-lm",
"pythia",
"pythia_v0",
"en",
"dataset:EleutherAI/the_pile_deduplicated",
"arxiv:2101.00027",
"arxiv:2201.07311",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | "2022-10-18T03:03:34Z" | ---
language:
- en
tags:
- pytorch
- causal-lm
- pythia
- pythia_v0
license: apache-2.0
datasets:
- EleutherAI/the_pile_deduplicated
---
The *Pythia Scaling Suite* is a collection of models developed to facilitate
interpretability research. It contains two sets of eight models of sizes
70M, 160M, 410M, 1B, 1.4B, 2.8B, 6.9B, and 12B. For each size, there are two
models: one trained on the Pile, and one trained on the Pile after the dataset
has been globally deduplicated. All 8 model sizes are trained on the exact
same data, in the exact same order. All Pythia models are available
[on Hugging Face](https://huggingface.co/models?other=pythia).
The Pythia model suite was deliberately designed to promote scientific
research on large language models, especially interpretability research.
Despite not centering downstream performance as a design goal, we find the
models <a href="#evaluations">match or exceed</a> the performance of
similar and same-sized models, such as those in the OPT and GPT-Neo suites.
Please note that all models in the *Pythia* suite were renamed in January
2023. For clarity, a <a href="#naming-convention-and-parameter-count">table
comparing the old and new names</a> is provided in this model card, together
with exact parameter counts.
## Pythia-1.4B-deduped
### Model Details
- Developed by: [EleutherAI](http://eleuther.ai)
- Model type: Transformer-based Language Model
- Language: English
- Learn more: [Pythia's GitHub repository](https://github.com/EleutherAI/pythia)
for training procedure, config files, and details on how to use.
- Library: [GPT-NeoX](https://github.com/EleutherAI/gpt-neox)
- License: Apache 2.0
- Contact: to ask questions about this model, join the [EleutherAI
Discord](https://discord.gg/zBGx3azzUn), and post them in `#release-discussion`.
Please read the existing *Pythia* documentation before asking about it in the
EleutherAI Discord. For general correspondence: [contact@eleuther.
ai](mailto:contact@eleuther.ai).
<figure>
| Pythia model | Non-Embedding Params | Layers | Model Dim | Heads | Batch Size | Learning Rate | Equivalent Models |
| -----------: | -------------------: | :----: | :-------: | :---: | :--------: | :-------------------: | :--------------------: |
| 70M | 18,915,328 | 6 | 512 | 8 | 2M | 1.0 x 10<sup>-3</sup> | — |
| 160M | 85,056,000 | 12 | 768 | 12 | 4M | 6.0 x 10<sup>-4</sup> | GPT-Neo 125M, OPT-125M |
| 410M | 302,311,424 | 24 | 1024 | 16 | 4M | 3.0 x 10<sup>-4</sup> | OPT-350M |
| 1.0B | 805,736,448 | 16 | 2048 | 8 | 2M | 3.0 x 10<sup>-4</sup> | — |
| 1.4B | 1,208,602,624 | 24 | 2048 | 16 | 4M | 2.0 x 10<sup>-4</sup> | GPT-Neo 1.3B, OPT-1.3B |
| 2.8B | 2,517,652,480 | 32 | 2560 | 32 | 2M | 1.6 x 10<sup>-4</sup> | GPT-Neo 2.7B, OPT-2.7B |
| 6.9B | 6,444,163,072 | 32 | 4096 | 32 | 2M | 1.2 x 10<sup>-4</sup> | OPT-6.7B |
| 12B | 11,327,027,200 | 36 | 5120 | 40 | 2M | 1.2 x 10<sup>-4</sup> | — |
<figcaption>Engineering details for the <i>Pythia Suite</i>. Deduped and
non-deduped models of a given size have the same hyperparameters. “Equivalent”
models have <b>exactly</b> the same architecture, and the same number of
non-embedding parameters.</figcaption>
</figure>
### Uses and Limitations
#### Intended Use
The primary intended use of Pythia is research on the behavior, functionality,
and limitations of large language models. This suite is intended to provide
a controlled setting for performing scientific experiments. To enable the
study of how language models change in the course of training, we provide
143 evenly spaced intermediate checkpoints per model. These checkpoints are
hosted on Hugging Face as branches. Note that branch `143000` corresponds
exactly to the model checkpoint on the `main` branch of each model.
You may also further fine-tune and adapt Pythia-1.4B-deduped for deployment,
as long as your use is in accordance with the Apache 2.0 license. Pythia
models work with the Hugging Face [Transformers
Library](https://huggingface.co/docs/transformers/index). If you decide to use
pre-trained Pythia-1.4B-deduped as a basis for your fine-tuned model, please
conduct your own risk and bias assessment.
#### Out-of-scope use
The Pythia Suite is **not** intended for deployment. It is not a in itself
a product and cannot be used for human-facing interactions.
Pythia models are English-language only, and are not suitable for translation
or generating text in other languages.
Pythia-1.4B-deduped has not been fine-tuned for downstream contexts in which
language models are commonly deployed, such as writing genre prose,
or commercial chatbots. This means Pythia-1.4B-deduped will **not**
respond to a given prompt the way a product like ChatGPT does. This is because,
unlike this model, ChatGPT was fine-tuned using methods such as Reinforcement
Learning from Human Feedback (RLHF) to better “understand” human instructions.
#### Limitations and biases
The core functionality of a large language model is to take a string of text
and predict the next token. The token deemed statistically most likely by the
model need not produce the most “accurate” text. Never rely on
Pythia-1.4B-deduped to produce factually accurate output.
This model was trained on [the Pile](https://pile.eleuther.ai/), a dataset
known to contain profanity and texts that are lewd or otherwise offensive.
See [Section 6 of the Pile paper](https://arxiv.org/abs/2101.00027) for a
discussion of documented biases with regards to gender, religion, and race.
Pythia-1.4B-deduped may produce socially unacceptable or undesirable text,
*even if* the prompt itself does not include anything explicitly offensive.
If you plan on using text generated through, for example, the Hosted Inference
API, we recommend having a human curate the outputs of this language model
before presenting it to other people. Please inform your audience that the
text was generated by Pythia-1.4B-deduped.
### Quickstart
Pythia models can be loaded and used via the following code, demonstrated here
for the third `pythia-70m-deduped` checkpoint:
```python
from transformers import GPTNeoXForCausalLM, AutoTokenizer
model = GPTNeoXForCausalLM.from_pretrained(
"EleutherAI/pythia-70m-deduped",
revision="step3000",
cache_dir="./pythia-70m-deduped/step3000",
)
tokenizer = AutoTokenizer.from_pretrained(
"EleutherAI/pythia-70m-deduped",
revision="step3000",
cache_dir="./pythia-70m-deduped/step3000",
)
inputs = tokenizer("Hello, I am", return_tensors="pt")
tokens = model.generate(**inputs)
tokenizer.decode(tokens[0])
```
Revision/branch `step143000` corresponds exactly to the model checkpoint on
the `main` branch of each model.<br>
For more information on how to use all Pythia models, see [documentation on
GitHub](https://github.com/EleutherAI/pythia).
### Training
#### Training data
Pythia-1.4B-deduped was trained on the Pile **after the dataset has been
globally deduplicated**.<br>
[The Pile](https://pile.eleuther.ai/) is a 825GiB general-purpose dataset in
English. It was created by EleutherAI specifically for training large language
models. It contains texts from 22 diverse sources, roughly broken down into
five categories: academic writing (e.g. arXiv), internet (e.g. CommonCrawl),
prose (e.g. Project Gutenberg), dialogue (e.g. YouTube subtitles), and
miscellaneous (e.g. GitHub, Enron Emails). See [the Pile
paper](https://arxiv.org/abs/2101.00027) for a breakdown of all data sources,
methodology, and a discussion of ethical implications. Consult [the
datasheet](https://arxiv.org/abs/2201.07311) for more detailed documentation
about the Pile and its component datasets. The Pile can be downloaded from
the [official website](https://pile.eleuther.ai/), or from a [community
mirror](https://the-eye.eu/public/AI/pile/).
#### Training procedure
All models were trained on the exact same data, in the exact same order. Each
model saw 299,892,736,000 tokens during training, and 143 checkpoints for each
model are saved every 2,097,152,000 tokens, spaced evenly throughout training.
This corresponds to training for just under 1 epoch on the Pile for
non-deduplicated models, and about 1.5 epochs on the deduplicated Pile.
All *Pythia* models trained for the equivalent of 143000 steps at a batch size
of 2,097,152 tokens. Two batch sizes were used: 2M and 4M. Models with a batch
size of 4M tokens listed were originally trained for 71500 steps instead, with
checkpoints every 500 steps. The checkpoints on Hugging Face are renamed for
consistency with all 2M batch models, so `step1000` is the first checkpoint
for `pythia-1.4b` that was saved (corresponding to step 500 in training), and
`step1000` is likewise the first `pythia-6.9b` checkpoint that was saved
(corresponding to 1000 “actual” steps).<br>
See [GitHub](https://github.com/EleutherAI/pythia) for more details on training
procedure, including [how to reproduce
it](https://github.com/EleutherAI/pythia/blob/main/README.md#reproducing-training).<br>
Pythia uses the same tokenizer as [GPT-NeoX-
20B](https://huggingface.co/EleutherAI/gpt-neox-20b).
### Evaluations
All 16 *Pythia* models were evaluated using the [LM Evaluation
Harness](https://github.com/EleutherAI/lm-evaluation-harness). You can access
the results by model and step at `results/json/*` in the [GitHub
repository](https://github.com/EleutherAI/pythia/tree/main/results/json).<br>
Expand the sections below to see plots of evaluation results for all
Pythia and Pythia-deduped models compared with OPT and BLOOM.
<details>
<summary>LAMBADA – OpenAI</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/lambada_openai.png" style="width:auto"/>
</details>
<details>
<summary>Physical Interaction: Question Answering (PIQA)</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/piqa.png" style="width:auto"/>
</details>
<details>
<summary>WinoGrande</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/winogrande.png" style="width:auto"/>
</details>
<details>
<summary>AI2 Reasoning Challenge – Challenge Set</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/arc_challenge.png" style="width:auto"/>
</details>
<details>
<summary>SciQ</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/sciq.png" style="width:auto"/>
</details>
### Naming convention and parameter count
*Pythia* models were renamed in January 2023. It is possible that the old
naming convention still persists in some documentation by accident. The
current naming convention (70M, 160M, etc.) is based on total parameter count.
<figure style="width:32em">
| current Pythia suffix | old suffix | total params | non-embedding params |
| --------------------: | ---------: | -------------: | -------------------: |
| 70M | 19M | 70,426,624 | 18,915,328 |
| 160M | 125M | 162,322,944 | 85,056,000 |
| 410M | 350M | 405,334,016 | 302,311,424 |
| 1B | 800M | 1,011,781,632 | 805,736,448 |
| 1.4B | 1.3B | 1,414,647,808 | 1,208,602,624 |
| 2.8B | 2.7B | 2,775,208,960 | 2,517,652,480 |
| 6.9B | 6.7B | 6,857,302,016 | 6,444,163,072 |
| 12B | 13B | 11,846,072,320 | 11,327,027,200 |
</figure> |
EleutherAI/pythia-410m | EleutherAI | "2023-07-09T16:01:42Z" | 68,125 | 22 | transformers | [
"transformers",
"pytorch",
"safetensors",
"gpt_neox",
"text-generation",
"causal-lm",
"pythia",
"en",
"dataset:EleutherAI/pile",
"arxiv:2304.01373",
"arxiv:2101.00027",
"arxiv:2201.07311",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | "2023-02-13T18:45:00Z" | ---
language:
- en
tags:
- pytorch
- causal-lm
- pythia
license: apache-2.0
datasets:
- EleutherAI/pile
---
The *Pythia Scaling Suite* is a collection of models developed to facilitate
interpretability research [(see paper)](https://arxiv.org/pdf/2304.01373.pdf).
It contains two sets of eight models of sizes
70M, 160M, 410M, 1B, 1.4B, 2.8B, 6.9B, and 12B. For each size, there are two
models: one trained on the Pile, and one trained on the Pile after the dataset
has been globally deduplicated. All 8 model sizes are trained on the exact
same data, in the exact same order. We also provide 154 intermediate
checkpoints per model, hosted on Hugging Face as branches.
The Pythia model suite was deliberately designed to promote scientific
research on large language models, especially interpretability research.
Despite not centering downstream performance as a design goal, we find the
models <a href="#evaluations">match or exceed</a> the performance of
similar and same-sized models, such as those in the OPT and GPT-Neo suites.
<details>
<summary style="font-weight:600">Details on previous early release and naming convention.</summary>
Previously, we released an early version of the Pythia suite to the public.
However, we decided to retrain the model suite to address a few hyperparameter
discrepancies. This model card <a href="#changelog">lists the changes</a>;
see appendix B in the Pythia paper for further discussion. We found no
difference in benchmark performance between the two Pythia versions.
The old models are
[still available](https://huggingface.co/models?other=pythia_v0), but we
suggest the retrained suite if you are just starting to use Pythia.<br>
**This is the current release.**
Please note that all models in the *Pythia* suite were renamed in January
2023. For clarity, a <a href="#naming-convention-and-parameter-count">table
comparing the old and new names</a> is provided in this model card, together
with exact parameter counts.
</details>
<br>
# Pythia-410M
## Model Details
- Developed by: [EleutherAI](http://eleuther.ai)
- Model type: Transformer-based Language Model
- Language: English
- Learn more: [Pythia's GitHub repository](https://github.com/EleutherAI/pythia)
for training procedure, config files, and details on how to use.
[See paper](https://arxiv.org/pdf/2304.01373.pdf) for more evals and implementation
details.
- Library: [GPT-NeoX](https://github.com/EleutherAI/gpt-neox)
- License: Apache 2.0
- Contact: to ask questions about this model, join the [EleutherAI
Discord](https://discord.gg/zBGx3azzUn), and post them in `#release-discussion`.
Please read the existing *Pythia* documentation before asking about it in the
EleutherAI Discord. For general correspondence: [contact@eleuther.
ai](mailto:contact@eleuther.ai).
<figure>
| Pythia model | Non-Embedding Params | Layers | Model Dim | Heads | Batch Size | Learning Rate | Equivalent Models |
| -----------: | -------------------: | :----: | :-------: | :---: | :--------: | :-------------------: | :--------------------: |
| 70M | 18,915,328 | 6 | 512 | 8 | 2M | 1.0 x 10<sup>-3</sup> | — |
| 160M | 85,056,000 | 12 | 768 | 12 | 2M | 6.0 x 10<sup>-4</sup> | GPT-Neo 125M, OPT-125M |
| 410M | 302,311,424 | 24 | 1024 | 16 | 2M | 3.0 x 10<sup>-4</sup> | OPT-350M |
| 1.0B | 805,736,448 | 16 | 2048 | 8 | 2M | 3.0 x 10<sup>-4</sup> | — |
| 1.4B | 1,208,602,624 | 24 | 2048 | 16 | 2M | 2.0 x 10<sup>-4</sup> | GPT-Neo 1.3B, OPT-1.3B |
| 2.8B | 2,517,652,480 | 32 | 2560 | 32 | 2M | 1.6 x 10<sup>-4</sup> | GPT-Neo 2.7B, OPT-2.7B |
| 6.9B | 6,444,163,072 | 32 | 4096 | 32 | 2M | 1.2 x 10<sup>-4</sup> | OPT-6.7B |
| 12B | 11,327,027,200 | 36 | 5120 | 40 | 2M | 1.2 x 10<sup>-4</sup> | — |
<figcaption>Engineering details for the <i>Pythia Suite</i>. Deduped and
non-deduped models of a given size have the same hyperparameters. “Equivalent”
models have <b>exactly</b> the same architecture, and the same number of
non-embedding parameters.</figcaption>
</figure>
## Uses and Limitations
### Intended Use
The primary intended use of Pythia is research on the behavior, functionality,
and limitations of large language models. This suite is intended to provide
a controlled setting for performing scientific experiments. We also provide
154 checkpoints per model: initial `step0`, 10 log-spaced checkpoints
`step{1,2,4...512}`, and 143 evenly-spaced checkpoints from `step1000` to
`step143000`. These checkpoints are hosted on Hugging Face as branches. Note
that branch `143000` corresponds exactly to the model checkpoint on the `main`
branch of each model.
You may also further fine-tune and adapt Pythia-410M for deployment,
as long as your use is in accordance with the Apache 2.0 license. Pythia
models work with the Hugging Face [Transformers
Library](https://huggingface.co/docs/transformers/index). If you decide to use
pre-trained Pythia-410M as a basis for your fine-tuned model, please
conduct your own risk and bias assessment.
### Out-of-scope use
The Pythia Suite is **not** intended for deployment. It is not a in itself
a product and cannot be used for human-facing interactions. For example,
the model may generate harmful or offensive text. Please evaluate the risks
associated with your particular use case.
Pythia models are English-language only, and are not suitable for translation
or generating text in other languages.
Pythia-410M has not been fine-tuned for downstream contexts in which
language models are commonly deployed, such as writing genre prose,
or commercial chatbots. This means Pythia-410M will **not**
respond to a given prompt the way a product like ChatGPT does. This is because,
unlike this model, ChatGPT was fine-tuned using methods such as Reinforcement
Learning from Human Feedback (RLHF) to better “follow” human instructions.
### Limitations and biases
The core functionality of a large language model is to take a string of text
and predict the next token. The token used by the model need not produce the
most “accurate” text. Never rely on Pythia-410M to produce factually accurate
output.
This model was trained on [the Pile](https://pile.eleuther.ai/), a dataset
known to contain profanity and texts that are lewd or otherwise offensive.
See [Section 6 of the Pile paper](https://arxiv.org/abs/2101.00027) for a
discussion of documented biases with regards to gender, religion, and race.
Pythia-410M may produce socially unacceptable or undesirable text, *even if*
the prompt itself does not include anything explicitly offensive.
If you plan on using text generated through, for example, the Hosted Inference
API, we recommend having a human curate the outputs of this language model
before presenting it to other people. Please inform your audience that the
text was generated by Pythia-410M.
### Quickstart
Pythia models can be loaded and used via the following code, demonstrated here
for the third `pythia-70m-deduped` checkpoint:
```python
from transformers import GPTNeoXForCausalLM, AutoTokenizer
model = GPTNeoXForCausalLM.from_pretrained(
"EleutherAI/pythia-70m-deduped",
revision="step3000",
cache_dir="./pythia-70m-deduped/step3000",
)
tokenizer = AutoTokenizer.from_pretrained(
"EleutherAI/pythia-70m-deduped",
revision="step3000",
cache_dir="./pythia-70m-deduped/step3000",
)
inputs = tokenizer("Hello, I am", return_tensors="pt")
tokens = model.generate(**inputs)
tokenizer.decode(tokens[0])
```
Revision/branch `step143000` corresponds exactly to the model checkpoint on
the `main` branch of each model.<br>
For more information on how to use all Pythia models, see [documentation on
GitHub](https://github.com/EleutherAI/pythia).
## Training
### Training data
[The Pile](https://pile.eleuther.ai/) is a 825GiB general-purpose dataset in
English. It was created by EleutherAI specifically for training large language
models. It contains texts from 22 diverse sources, roughly broken down into
five categories: academic writing (e.g. arXiv), internet (e.g. CommonCrawl),
prose (e.g. Project Gutenberg), dialogue (e.g. YouTube subtitles), and
miscellaneous (e.g. GitHub, Enron Emails). See [the Pile
paper](https://arxiv.org/abs/2101.00027) for a breakdown of all data sources,
methodology, and a discussion of ethical implications. Consult [the
datasheet](https://arxiv.org/abs/2201.07311) for more detailed documentation
about the Pile and its component datasets. The Pile can be downloaded from
the [official website](https://pile.eleuther.ai/), or from a [community
mirror](https://the-eye.eu/public/AI/pile/).<br>
The Pile was **not** deduplicated before being used to train Pythia-410M.
### Training procedure
All models were trained on the exact same data, in the exact same order. Each
model saw 299,892,736,000 tokens during training, and 143 checkpoints for each
model are saved every 2,097,152,000 tokens, spaced evenly throughout training,
from `step1000` to `step143000` (which is the same as `main`). In addition, we
also provide frequent early checkpoints: `step0` and `step{1,2,4...512}`.
This corresponds to training for just under 1 epoch on the Pile for
non-deduplicated models, and about 1.5 epochs on the deduplicated Pile.
All *Pythia* models trained for 143000 steps at a batch size
of 2M (2,097,152 tokens).<br>
See [GitHub](https://github.com/EleutherAI/pythia) for more details on training
procedure, including [how to reproduce
it](https://github.com/EleutherAI/pythia/blob/main/README.md#reproducing-training).<br>
Pythia uses the same tokenizer as [GPT-NeoX-
20B](https://huggingface.co/EleutherAI/gpt-neox-20b).
## Evaluations
All 16 *Pythia* models were evaluated using the [LM Evaluation
Harness](https://github.com/EleutherAI/lm-evaluation-harness). You can access
the results by model and step at `results/json/*` in the [GitHub
repository](https://github.com/EleutherAI/pythia/tree/main/results/json/).<br>
Expand the sections below to see plots of evaluation results for all
Pythia and Pythia-deduped models compared with OPT and BLOOM.
<details>
<summary>LAMBADA – OpenAI</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/lambada_openai_v1.png" style="width:auto"/>
</details>
<details>
<summary>Physical Interaction: Question Answering (PIQA)</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/piqa_v1.png" style="width:auto"/>
</details>
<details>
<summary>WinoGrande</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/winogrande_v1.png" style="width:auto"/>
</details>
<details>
<summary>AI2 Reasoning Challenge—Easy Set</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/arc_easy_v1.png" style="width:auto"/>
</details>
<details>
<summary>SciQ</summary>
<img src="/EleutherAI/pythia-12b/resolve/main/eval_plots/sciq_v1.png" style="width:auto"/>
</details>
## Changelog
This section compares differences between previously released
[Pythia v0](https://huggingface.co/models?other=pythia_v0) and the current
models. See Appendix B of the Pythia paper for further discussion of these
changes and the motivation behind them. We found that retraining Pythia had no
impact on benchmark performance.
- All model sizes are now trained with uniform batch size of 2M tokens.
Previously, the models of size 160M, 410M, and 1.4B parameters were trained
with batch sizes of 4M tokens.
- We added checkpoints at initialization (step 0) and steps {1,2,4,8,16,32,64,
128,256,512} in addition to every 1000 training steps.
- Flash Attention was used in the new retrained suite.
- We remedied a minor inconsistency that existed in the original suite: all
models of size 2.8B parameters or smaller had a learning rate (LR) schedule
which decayed to a minimum LR of 10% the starting LR rate, but the 6.9B and
12B models all used an LR schedule which decayed to a minimum LR of 0. In
the redone training runs, we rectified this inconsistency: all models now were
trained with LR decaying to a minimum of 0.1× their maximum LR.
### Naming convention and parameter count
*Pythia* models were renamed in January 2023. It is possible that the old
naming convention still persists in some documentation by accident. The
current naming convention (70M, 160M, etc.) is based on total parameter count.
<figure style="width:32em">
| current Pythia suffix | old suffix | total params | non-embedding params |
| --------------------: | ---------: | -------------: | -------------------: |
| 70M | 19M | 70,426,624 | 18,915,328 |
| 160M | 125M | 162,322,944 | 85,056,000 |
| 410M | 350M | 405,334,016 | 302,311,424 |
| 1B | 800M | 1,011,781,632 | 805,736,448 |
| 1.4B | 1.3B | 1,414,647,808 | 1,208,602,624 |
| 2.8B | 2.7B | 2,775,208,960 | 2,517,652,480 |
| 6.9B | 6.7B | 6,857,302,016 | 6,444,163,072 |
| 12B | 13B | 11,846,072,320 | 11,327,027,200 |
</figure> |
cagarraz/poca-SoccerTwos | cagarraz | "2023-07-09T16:01:25Z" | 0 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"SoccerTwos",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-SoccerTwos",
"region:us"
] | reinforcement-learning | "2023-07-09T16:01:19Z" | ---
library_name: ml-agents
tags:
- SoccerTwos
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-SoccerTwos
---
# **poca** Agent playing **SoccerTwos**
This is a trained model of a **poca** agent playing **SoccerTwos**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: cagarraz/poca-SoccerTwos
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
carybr/ppo-Huggy | carybr | "2023-07-09T15:37:56Z" | 9 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] | reinforcement-learning | "2023-07-09T15:37:52Z" | ---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: carybr/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
afterthougt/kullm-polyglot-12.8b-v2_700steps | afterthougt | "2023-07-09T15:31:45Z" | 5 | 0 | peft | [
"peft",
"gpt_neox",
"region:us"
] | null | "2023-07-06T05:04:33Z" | ---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.4.0.dev0
|
lordtt13/blenderbot_small-news | lordtt13 | "2023-07-09T15:28:39Z" | 111 | 0 | transformers | [
"transformers",
"pytorch",
"tf",
"safetensors",
"blenderbot-small",
"text2text-generation",
"en",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text2text-generation | "2022-03-02T23:29:05Z" | ---
language: en
---
## BlenderBotSmall-News: Small version of a state-of-the-art open source chatbot, trained on custom summaries
### Details of BlenderBotSmall
The **BlenderBotSmall** model was presented in [A state-of-the-art open source chatbot](https://ai.facebook.com/blog/state-of-the-art-open-source-chatbot/) by *Facebook AI* and here are it's details:
- Facebook AI has built and open-sourced BlenderBot, the largest-ever open-domain chatbot. It outperforms others in terms of engagement and also feels more human, according to human evaluators.
- The culmination of years of research in conversational AI, this is the first chatbot to blend a diverse set of conversational skills — including empathy, knowledge, and personality — together in one system.
- We achieved this milestone through a new chatbot recipe that includes improved decoding techniques, novel blending of skills, and a model with 9.4 billion parameters, which is 3.6x more than the largest existing system.
### Details of the downstream task (Summarization) - Dataset 📚
A custom dataset was used, which was hand prepared by [SmokeTrees Digital](https://github.com/smoke-trees) AI engineers. This data contains long texts and summaries.
### Model training
The training script is present [here](https://github.com/lordtt13/transformers-experiments/blob/master/Custom%20Tasks/fine-tune-blenderbot_small-for-summarization.ipynb).
### Pipelining the Model
```python
model = transformers.BlenderbotSmallForConditionalGeneration.from_pretrained('lordtt13/blenderbot_small-news')
tokenizer = transformers.BlenderbotSmallTokenizer.from_pretrained("lordtt13/blenderbot_small-news")
nlp_fill = transformers.pipeline('summarization', model = model, tokenizer = tokenizer)
nlp_fill('The CBI on Saturday booked four former officials of Syndicate Bank and six others for cheating, forgery, criminal conspiracy and causing ₹209 crore loss to the state-run bank. The accused had availed home loans and credit from Syndicate Bank on the basis of forged and fabricated documents. These funds were fraudulently transferred to the companies owned by the accused persons.', min_length=5, max_length=40)
# Output:
# [{'summary_text': 'marize: the cbi booked four former officials of syndicate bank and six others for cheating , forgery , criminal conspiracy and causing 209 crore loss to the staterun bank'}]
```
> Created by [Tanmay Thakur](https://github.com/lordtt13) | [LinkedIn](https://www.linkedin.com/in/tanmay-thakur-6bb5a9154/)
|
lordtt13/emo-mobilebert | lordtt13 | "2023-07-09T15:28:20Z" | 3,195 | 3 | transformers | [
"transformers",
"pytorch",
"tf",
"safetensors",
"mobilebert",
"text-classification",
"en",
"dataset:emo",
"arxiv:2004.02984",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | "2022-03-02T23:29:05Z" | ---
language: en
datasets:
- emo
---
## Emo-MobileBERT: a thin version of BERT LARGE, trained on the EmoContext Dataset from scratch
### Details of MobileBERT
The **MobileBERT** model was presented in [MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices](https://arxiv.org/abs/2004.02984) by *Zhiqing Sun, Hongkun Yu, Xiaodan Song, Renjie Liu, Yiming Yang, Denny Zhou* and here is the abstract:
Natural Language Processing (NLP) has recently achieved great success by using huge pre-trained models with hundreds of millions of parameters. However, these models suffer from heavy model sizes and high latency such that they cannot be deployed to resource-limited mobile devices. In this paper, we propose MobileBERT for compressing and accelerating the popular BERT model. Like the original BERT, MobileBERT is task-agnostic, that is, it can be generically applied to various downstream NLP tasks via simple fine-tuning. Basically, MobileBERT is a thin version of BERT_LARGE, while equipped with bottleneck structures and a carefully designed balance between self-attentions and feed-forward networks. To train MobileBERT, we first train a specially designed teacher model, an inverted-bottleneck incorporated BERT_LARGE model. Then, we conduct knowledge transfer from this teacher to MobileBERT. Empirical studies show that MobileBERT is 4.3x smaller and 5.5x faster than BERT_BASE while achieving competitive results on well-known benchmarks. On the natural language inference tasks of GLUE, MobileBERT achieves a GLUEscore o 77.7 (0.6 lower than BERT_BASE), and 62 ms latency on a Pixel 4 phone. On the SQuAD v1.1/v2.0 question answering task, MobileBERT achieves a dev F1 score of 90.0/79.2 (1.5/2.1 higher than BERT_BASE).
### Details of the downstream task (Emotion Recognition) - Dataset 📚
SemEval-2019 Task 3: EmoContext Contextual Emotion Detection in Text
In this dataset, given a textual dialogue i.e. an utterance along with two previous turns of context, the goal was to infer the underlying emotion of the utterance by choosing from four emotion classes:
- sad 😢
- happy 😃
- angry 😡
- others
### Model training
The training script is present [here](https://github.com/lordtt13/transformers-experiments/blob/master/Custom%20Tasks/emo-mobilebert.ipynb).
### Pipelining the Model
```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
tokenizer = AutoTokenizer.from_pretrained("lordtt13/emo-mobilebert")
model = AutoModelForSequenceClassification.from_pretrained("lordtt13/emo-mobilebert")
nlp_sentence_classif = transformers.pipeline('sentiment-analysis', model = model, tokenizer = tokenizer)
nlp_sentence_classif("I've never had such a bad day in my life")
# Output: [{'label': 'sad', 'score': 0.93153977394104}]
```
> Created by [Tanmay Thakur](https://github.com/lordtt13) | [LinkedIn](https://www.linkedin.com/in/tanmay-thakur-6bb5a9154/)
|
Sekiraw/Ant | Sekiraw | "2023-07-09T15:16:55Z" | 2 | 0 | stable-baselines3 | [
"stable-baselines3",
"AntBulletEnv-v0",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | "2023-07-09T15:15:10Z" | ---
library_name: stable-baselines3
tags:
- AntBulletEnv-v0
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: A2C
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: AntBulletEnv-v0
type: AntBulletEnv-v0
metrics:
- type: mean_reward
value: 2548.33 +/- 83.37
name: mean_reward
verified: false
---
# **A2C** Agent playing **AntBulletEnv-v0**
This is a trained model of a **A2C** agent playing **AntBulletEnv-v0**
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
```python
from stable_baselines3 import ...
from huggingface_sb3 import load_from_hub
...
```
|
Sekiraw/doom | Sekiraw | "2023-07-09T15:12:54Z" | 0 | 0 | stable-baselines3 | [
"stable-baselines3",
"VizdoomBasic-v0",
"deep-reinforcement-learning",
"reinforcement-learning",
"model-index",
"region:us"
] | reinforcement-learning | "2023-07-09T15:07:55Z" | ---
library_name: stable-baselines3
tags:
- VizdoomBasic-v0
- deep-reinforcement-learning
- reinforcement-learning
- stable-baselines3
model-index:
- name: ppo
results:
- metrics:
- type: mean_reward
value: -209.90 +/- 196.26
name: mean_reward
task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: VizdoomBasic-v0
type: VizdoomBasic-v0
---
# **ppo** Agent playing **VizdoomBasic-v0**
This is a trained model of a **ppo** agent playing **VizdoomBasic-v0** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
## Usage (with Stable-baselines3)
TODO: Add your code
|
Officialletai/Reinforce-CartPole-v1 | Officialletai | "2023-07-09T15:10:23Z" | 0 | 0 | null | [
"CartPole-v1",
"reinforce",
"reinforcement-learning",
"custom-implementation",
"deep-rl-class",
"model-index",
"region:us"
] | reinforcement-learning | "2023-07-09T15:10:15Z" | ---
tags:
- CartPole-v1
- reinforce
- reinforcement-learning
- custom-implementation
- deep-rl-class
model-index:
- name: Reinforce-CartPole-v1
results:
- task:
type: reinforcement-learning
name: reinforcement-learning
dataset:
name: CartPole-v1
type: CartPole-v1
metrics:
- type: mean_reward
value: 500.00 +/- 0.00
name: mean_reward
verified: false
---
# **Reinforce** Agent playing **CartPole-v1**
This is a trained model of a **Reinforce** agent playing **CartPole-v1** .
To learn to use this model and train yours check Unit 4 of the Deep Reinforcement Learning Course: https://huggingface.co/deep-rl-course/unit4/introduction
|
Gorttham/flan-t5-small-chat | Gorttham | "2023-07-09T15:07:44Z" | 111 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"t5",
"text2text-generation",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text2text-generation | "2023-07-02T10:11:21Z" | ---
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: content
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# content
This model is a fine-tuned version of [google/flan-t5-small](https://huggingface.co/google/flan-t5-small) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 2.5985
- Rouge1: 32.7607
- Rouge2: 19.5507
- Rougel: 32.7312
- Rougelsum: 32.7306
- Gen Len: 16.4212
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 4
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
| 3.043 | 1.0 | 1348 | 2.7636 | 34.4245 | 20.9962 | 34.386 | 34.3876 | 15.1150 |
| 2.8078 | 2.0 | 2696 | 2.6540 | 32.5342 | 19.3983 | 32.4966 | 32.4947 | 16.7662 |
| 2.7166 | 3.0 | 4044 | 2.6103 | 32.4564 | 19.3597 | 32.4255 | 32.4355 | 16.6037 |
| 2.6876 | 4.0 | 5392 | 2.5985 | 32.7607 | 19.5507 | 32.7312 | 32.7306 | 16.4212 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
chunwoolee0/my_awesome_eli5_clm-model | chunwoolee0 | "2023-07-09T15:06:15Z" | 141 | 0 | transformers | [
"transformers",
"pytorch",
"tensorboard",
"gpt2",
"text-generation",
"generated_from_trainer",
"license:apache-2.0",
"autotrain_compatible",
"text-generation-inference",
"endpoints_compatible",
"region:us"
] | text-generation | "2023-07-09T11:57:24Z" | ---
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: my_awesome_eli5_clm-model
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# my_awesome_eli5_clm-model
This model is a fine-tuned version of [distilgpt2](https://huggingface.co/distilgpt2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 3.7493
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 3.7059 | 1.0 | 1108 | 3.7527 |
| 3.6588 | 2.0 | 2216 | 3.7516 |
| 3.6291 | 3.0 | 3324 | 3.7493 |
### Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu118
- Datasets 2.13.1
- Tokenizers 0.13.3
|
aclodic/ppo-Huggy | aclodic | "2023-07-09T15:03:30Z" | 0 | 0 | ml-agents | [
"ml-agents",
"tensorboard",
"onnx",
"Huggy",
"deep-reinforcement-learning",
"reinforcement-learning",
"ML-Agents-Huggy",
"region:us"
] | reinforcement-learning | "2023-07-09T15:03:25Z" | ---
library_name: ml-agents
tags:
- Huggy
- deep-reinforcement-learning
- reinforcement-learning
- ML-Agents-Huggy
---
# **ppo** Agent playing **Huggy**
This is a trained model of a **ppo** agent playing **Huggy**
using the [Unity ML-Agents Library](https://github.com/Unity-Technologies/ml-agents).
## Usage (with ML-Agents)
The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/
We wrote a complete tutorial to learn to train your first agent using ML-Agents and publish it to the Hub:
- A *short tutorial* where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your
browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
- A *longer tutorial* to understand how works ML-Agents:
https://huggingface.co/learn/deep-rl-course/unit5/introduction
### Resume the training
```bash
mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume
```
### Watch your Agent play
You can watch your agent **playing directly in your browser**
1. If the environment is part of ML-Agents official environments, go to https://huggingface.co/unity
2. Step 1: Find your model_id: aclodic/ppo-Huggy
3. Step 2: Select your *.nn /*.onnx file
4. Click on Watch the agent play 👀
|
svetadomoi/alpaca-native-onex | svetadomoi | "2023-07-09T15:02:10Z" | 2 | 0 | peft | [
"peft",
"region:us"
] | null | "2023-07-09T14:23:44Z" | ---
library_name: peft
---
## Training procedure
The following `bitsandbytes` quantization config was used during training:
- load_in_8bit: False
- load_in_4bit: True
- llm_int8_threshold: 6.0
- llm_int8_skip_modules: None
- llm_int8_enable_fp32_cpu_offload: False
- llm_int8_has_fp16_weight: False
- bnb_4bit_quant_type: nf4
- bnb_4bit_use_double_quant: True
- bnb_4bit_compute_dtype: bfloat16
### Framework versions
- PEFT 0.4.0.dev0
|
gremlin97/ControlNetFill50k | gremlin97 | "2023-07-09T14:56:19Z" | 0 | 0 | null | [
"license:deepfloyd-if-license",
"region:us"
] | null | "2023-07-09T13:35:07Z" | ---
license: deepfloyd-if-license
---
This repo contains a Control Net model trained on the Fill-50k dataset. I have trained this model on a 2 A100 GPU cluster using distributed training enabled through PyTorch Lightning API. It has been trained for 1 epoch for a duration of 4-5 hours. The model achieves good results. |
mrtimmydontplay/PKthunda | mrtimmydontplay | "2023-07-09T14:53:37Z" | 0 | 0 | adapter-transformers | [
"adapter-transformers",
"en",
"license:other",
"region:us"
] | null | "2023-07-09T12:31:23Z" | ---
license: other
language:
- en
metrics:
- bleu
- accuracy
- code_eval
library_name: adapter-transformers
--- |
lunarti/distilbert-base-uncased-finetuned-cola | lunarti | "2023-07-09T14:49:11Z" | 61 | 0 | transformers | [
"transformers",
"tf",
"tensorboard",
"distilbert",
"text-classification",
"generated_from_keras_callback",
"license:apache-2.0",
"autotrain_compatible",
"endpoints_compatible",
"region:us"
] | text-classification | "2023-07-09T14:45:07Z" | ---
license: apache-2.0
tags:
- generated_from_keras_callback
model-index:
- name: lunarti/distilbert-base-uncased-finetuned-cola
results: []
---
<!-- This model card has been generated automatically according to the information Keras had access to. You should
probably proofread and complete it, then remove this comment. -->
# lunarti/distilbert-base-uncased-finetuned-cola
This model is a fine-tuned version of [distilbert-base-uncased](https://huggingface.co/distilbert-base-uncased) on an unknown dataset.
It achieves the following results on the evaluation set:
- Train Loss: 0.2100
- Validation Loss: 0.5140
- Train Matthews Correlation: 0.5116
- Epoch: 2
## Model description
More information needed
## Intended uses & limitations
More information needed
## Training and evaluation data
More information needed
## Training procedure
### Training hyperparameters
The following hyperparameters were used during training:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1602, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
### Training results
| Train Loss | Validation Loss | Train Matthews Correlation | Epoch |
|:----------:|:---------------:|:--------------------------:|:-----:|
| 0.5299 | 0.4771 | 0.4416 | 0 |
| 0.3324 | 0.4844 | 0.5051 | 1 |
| 0.2100 | 0.5140 | 0.5116 | 2 |
### Framework versions
- Transformers 4.30.2
- TensorFlow 2.12.0
- Datasets 2.13.1
- Tokenizers 0.13.3
|
Chocoboko/OTN_BDSM | Chocoboko | "2023-07-09T14:47:10Z" | 0 | 0 | null | [
"license:creativeml-openrail-m",
"region:us"
] | null | "2023-06-17T10:26:26Z" | ---
license: creativeml-openrail-m
---
|
Subsets and Splits