README.md

---
library_name: transformers
license: apache-2.0
datasets:
  - Open-Orca/slimorca-deduped-cleaned-corrected
language:
  - en
base_model:
  - Felladrin/Minueza-2-96M
tags:
  - llama-factory
---

# Minueza-2-96M-Instruct (Variant 07)

This model is a fine-tuned version of [Felladrin/Minueza-2-96M](https://huggingface.co/Felladrin/Minueza-2-96M) on the English [Open-Orca/slimorca-deduped-cleaned-corrected](https://huggingface.co/datasets/Open-Orca/slimorca-deduped-cleaned-corrected) dataset.

## Usage

```sh
pip install transformers==4.51.1 torch==2.6.0
```

```python
from transformers import pipeline, TextStreamer
import torch

generate_text = pipeline(
    "text-generation",
    model="Felladrin/Minueza-2-96M-Instruct-Variant-07",
    device=torch.device("cuda" if torch.cuda.is_available() else "cpu"),
)

messages = [
  {
    "role": "system",
    "content": "You are an AI assistant that follows instruction extremely well. Help as much as you can.",
  },
  {
    "role": "user",
    "content": "Could you explain how does the Internet work?",
  },
]

generate_text(
    generate_text.tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    ),
    streamer=TextStreamer(generate_text.tokenizer, skip_special_tokens=True),
    max_new_tokens=512,
    do_sample=True,
    temperature=0.7,
    top_p=0.9,
    top_k=0,
    min_p=0.1,
    repetition_penalty=1.17,
)
```

## Training hyperparameters

The following hyperparameters were used during training:

- learning_rate: 5.8e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 128
- optimizer: Use adamw_torch with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3

## Framework versions

- Transformers 4.51.1
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.0

## License

This model is licensed under the Apache License 2.0.