README.md

---
tags:
- pytorch
- trl
- sft
- mlx
inference: false
---

# mlx-community/omost-llama-3-8b-mlx-8bit

The Model [mlx-community/omost-llama-3-8b-mlx-8bit](https://huggingface.co/mlx-community/omost-llama-3-8b-mlx-8bit) was converted to MLX format from [lllyasviel/omost-llama-3-8b](https://huggingface.co/lllyasviel/omost-llama-3-8b) using mlx-lm version **0.14.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/omost-llama-3-8b-mlx-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```