README.md

---
library_name: transformers
license: llama3.1
language:
- ko
- vi
- id
- km
- th
metrics:
- bleu
- rouge
base_model: MLP-KTLim/llama-3.1-Asian-Bllossom-8B-Translator
tags:
- mlx
---

# Fmuaddib/llama-3.1-Asian-Bllossom-8B-Translator-mlx-fp16

The Model [Fmuaddib/llama-3.1-Asian-Bllossom-8B-Translator-mlx-fp16](https://huggingface.co/Fmuaddib/llama-3.1-Asian-Bllossom-8B-Translator-mlx-fp16) was converted to MLX format from [MLP-KTLim/llama-3.1-Asian-Bllossom-8B-Translator](https://huggingface.co/MLP-KTLim/llama-3.1-Asian-Bllossom-8B-Translator) using mlx-lm version **0.22.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("Fmuaddib/llama-3.1-Asian-Bllossom-8B-Translator-mlx-fp16")

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)
```