README.md

---
language:
- ru
datasets:
- IlyaGusev/saiga_scored
license: other
license_name: llama3
license_link: https://llama.meta.com/llama3/license/
tags:
- mlx
base_model: IlyaGusev/saiga_llama3_8b
---

# steamdroid/saiga_llama3_8b-mlx-4Bit

The Model [steamdroid/saiga_llama3_8b-mlx-4Bit](https://huggingface.co/steamdroid/saiga_llama3_8b-mlx-4Bit) was converted to MLX format from [IlyaGusev/saiga_llama3_8b](https://huggingface.co/IlyaGusev/saiga_llama3_8b) using mlx-lm version **0.26.3**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("steamdroid/saiga_llama3_8b-mlx-4Bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```