README.md

---
license: apache-2.0
language:
- en
base_model: DavidAU/Qwen2.5-2X32B-CoderInstruct-OlympicCoder-87B-v1.1
pipeline_tag: text-generation
tags:
- merge
- programming
- code generation
- code
- codeqwen
- moe
- coding
- coder
- qwen2
- chat
- qwen
- qwen-coder
- mixture of experts
- qwen2moe
- 2X32B Shared.
- shared expert
- mlx
library_name: mlx
---

# mlx-community/Qwen2.5-2X32B-CoderInstruct-OlympicCoder-87B-v1.1-4bit

This model [mlx-community/Qwen2.5-2X32B-CoderInstruct-OlympicCoder-87B-v1.1-4bit](https://huggingface.co/mlx-community/Qwen2.5-2X32B-CoderInstruct-OlympicCoder-87B-v1.1-4bit) was
converted to MLX format from [DavidAU/Qwen2.5-2X32B-CoderInstruct-OlympicCoder-87B-v1.1](https://huggingface.co/DavidAU/Qwen2.5-2X32B-CoderInstruct-OlympicCoder-87B-v1.1)
using mlx-lm version **0.25.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Qwen2.5-2X32B-CoderInstruct-OlympicCoder-87B-v1.1-4bit")

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)
```