Update README.md
Browse files
README.md
CHANGED
|
@@ -8,13 +8,18 @@ tags:
|
|
| 8 |
- large language model
|
| 9 |
- h2o-llmstudio
|
| 10 |
inference: false
|
| 11 |
-
thumbnail:
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
---
|
| 13 |
# Model Card
|
| 14 |
## Summary
|
| 15 |
|
| 16 |
This model was trained using [H2O LLM Studio](https://github.com/h2oai/h2o-llmstudio).
|
| 17 |
- Base model: [openlm-research/open_llama_3b](https://huggingface.co/openlm-research/open_llama_3b)
|
|
|
|
| 18 |
|
| 19 |
|
| 20 |
## Usage
|
|
@@ -22,7 +27,7 @@ This model was trained using [H2O LLM Studio](https://github.com/h2oai/h2o-llmst
|
|
| 22 |
To use the model with the `transformers` library on a machine with GPUs, first make sure you have the `transformers`, `accelerate` and `torch` libraries installed.
|
| 23 |
|
| 24 |
```bash
|
| 25 |
-
pip install transformers==4.
|
| 26 |
pip install accelerate==0.20.3
|
| 27 |
pip install torch==2.0.0
|
| 28 |
```
|
|
@@ -174,15 +179,6 @@ LlamaForCausalLM(
|
|
| 174 |
This model was trained using H2O LLM Studio and with the configuration in [cfg.yaml](cfg.yaml). Visit [H2O LLM Studio](https://github.com/h2oai/h2o-llmstudio) to learn how to train your own large language models.
|
| 175 |
|
| 176 |
|
| 177 |
-
## Model Validation
|
| 178 |
-
|
| 179 |
-
Model validation results using [EleutherAI lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness).
|
| 180 |
-
|
| 181 |
-
```bash
|
| 182 |
-
CUDA_VISIBLE_DEVICES=0 python main.py --model hf-causal-experimental --model_args pretrained=h2oai/h2ogpt-gm-oasst1-en-2048-open-llama-3b --tasks openbookqa,arc_easy,winogrande,hellaswag,arc_challenge,piqa,boolq --device cuda &> eval.log
|
| 183 |
-
```
|
| 184 |
-
|
| 185 |
-
|
| 186 |
## Disclaimer
|
| 187 |
|
| 188 |
Please read this disclaimer carefully before using the large language model provided in this repository. Your use of the model signifies your agreement to the following terms and conditions.
|
|
|
|
| 8 |
- large language model
|
| 9 |
- h2o-llmstudio
|
| 10 |
inference: false
|
| 11 |
+
thumbnail: >-
|
| 12 |
+
https://h2o.ai/etc.clientlibs/h2o/clientlibs/clientlib-site/resources/images/favicon.ico
|
| 13 |
+
license: apache-2.0
|
| 14 |
+
datasets:
|
| 15 |
+
- OpenAssistant/oasst1
|
| 16 |
---
|
| 17 |
# Model Card
|
| 18 |
## Summary
|
| 19 |
|
| 20 |
This model was trained using [H2O LLM Studio](https://github.com/h2oai/h2o-llmstudio).
|
| 21 |
- Base model: [openlm-research/open_llama_3b](https://huggingface.co/openlm-research/open_llama_3b)
|
| 22 |
+
- Dataset preparation: [OpenAssistant/oasst1](https://github.com/h2oai/h2o-llmstudio/blob/1935d84d9caafed3ee686ad2733eb02d2abfce57/app_utils/utils.py#LL1896C5-L1896C28)
|
| 23 |
|
| 24 |
|
| 25 |
## Usage
|
|
|
|
| 27 |
To use the model with the `transformers` library on a machine with GPUs, first make sure you have the `transformers`, `accelerate` and `torch` libraries installed.
|
| 28 |
|
| 29 |
```bash
|
| 30 |
+
pip install transformers==4.30.2
|
| 31 |
pip install accelerate==0.20.3
|
| 32 |
pip install torch==2.0.0
|
| 33 |
```
|
|
|
|
| 179 |
This model was trained using H2O LLM Studio and with the configuration in [cfg.yaml](cfg.yaml). Visit [H2O LLM Studio](https://github.com/h2oai/h2o-llmstudio) to learn how to train your own large language models.
|
| 180 |
|
| 181 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 182 |
## Disclaimer
|
| 183 |
|
| 184 |
Please read this disclaimer carefully before using the large language model provided in this repository. Your use of the model signifies your agreement to the following terms and conditions.
|