# DeepSeek-R1-4bit

**Repository Path**: zc2020/DeepSeek-R1-4bit

## Basic Information

- **Project Name**: DeepSeek-R1-4bit
- **Description**: Mirror of https://huggingface.co/mlx-community/DeepSeek-R1-4bit
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 2
- **Created**: 2025-02-10
- **Last Updated**: 2025-02-10

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

---
base_model: deepseek-ai/DeepSeek-R1
tags:
- mlx
---

# mlx-community/DeepSeek-R1-4bit

The Model [mlx-community/DeepSeek-R1-4bit](https://huggingface.co/mlx-community/DeepSeek-R1-4bit) was
converted to MLX format from [deepseek-ai/DeepSeek-R1](https://huggingface.co/deepseek-ai/DeepSeek-R1)
using mlx-lm version **0.21.0**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/DeepSeek-R1-4bit")

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)
```