README.md

---
license: apache-2.0
language:
- zh
- en
tags:
- qwen
- sales
- unsloth
- lora
- logic-tuning
- strategic-thinking
- mlx
pipeline_tag: text-generation
base_model: aifeifei798/QiMing-Think-4B-V1
library_name: mlx
---

# QiMing-Think-4B-V1-q6-mlx

This model [QiMing-Think-4B-V1-q6-mlx](https://huggingface.co/QiMing-Think-4B-V1-q6-mlx) was
converted to MLX format from [aifeifei798/QiMing-Think-4B-V1](https://huggingface.co/aifeifei798/QiMing-Think-4B-V1)
using mlx-lm version **0.26.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("QiMing-Think-4B-V1-q6-mlx")

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)
```