README.md

---
license: mit
language:
- en
base_model: fm-universe/qwen2.5-coder-7b-instruct-fma
tags:
- mlx
---

# danielcfho/qwen2.5-coder-7b-instruct-fma-bf16

The Model [danielcfho/qwen2.5-coder-7b-instruct-fma-bf16](https://huggingface.co./danielcfho/qwen2.5-coder-7b-instruct-fma-bf16) was
converted to MLX format from [fm-universe/qwen2.5-coder-7b-instruct-fma](https://huggingface.co./fm-universe/qwen2.5-coder-7b-instruct-fma)
using mlx-lm version **0.21.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("danielcfho/qwen2.5-coder-7b-instruct-fma-bf16")

prompt = "hello"

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

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