README.md

---
license: mit
license_link: https://huggingface.co/rednote-hilab/dots.llm1.inst/blob/main/LICENSE
pipeline_tag: text-generation
base_model: rednote-hilab/dots.llm1.inst
tags:
- chat
- mlx
library_name: mlx
language:
- en
- zh
---

# mlx-community/dots.llm1.inst-mixed-4-6bit

This model [mlx-community/dots.llm1.inst-mixed-4-6bit](https://huggingface.co/mlx-community/dots.llm1.inst-mixed-4-6bit) was
converted to MLX format from [rednote-hilab/dots.llm1.inst](https://huggingface.co/rednote-hilab/dots.llm1.inst)
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/dots.llm1.inst-mixed-4-6bit")

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)
```