README.md

---
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen2.5-7B-Instruct-1M/blob/main/LICENSE
language:
- en
pipeline_tag: text-generation
base_model: Qwen/Qwen2.5-7B-Instruct-1M
tags:
- chat
- mlx
library_name: transformers
---

# moot20/Qwen2.5-7B-Instruct-1M-MLX-6bits

The Model [moot20/Qwen2.5-7B-Instruct-1M-MLX-6bits](https://huggingface.co/moot20/Qwen2.5-7B-Instruct-1M-MLX-6bits) was
converted to MLX format from [Qwen/Qwen2.5-7B-Instruct-1M](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct-1M)
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("moot20/Qwen2.5-7B-Instruct-1M-MLX-6bits")

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)
```