README.md

---
license: other
license_name: deepseek-license
license_link: LICENSE
base_model: deepseek-ai/DeepSeek-Coder-V2-Instruct
tags:
- mlx
---

# nafisabdkhan/DeepSeek-Coder-V2-Instruct-mlx-2Bit

The Model [nafisabdkhan/DeepSeek-Coder-V2-Instruct-mlx-2Bit](https://huggingface.co/nafisabdkhan/DeepSeek-Coder-V2-Instruct-mlx-2Bit) was converted to MLX format from [deepseek-ai/DeepSeek-Coder-V2-Instruct](https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Instruct) using mlx-lm version **0.22.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("nafisabdkhan/DeepSeek-Coder-V2-Instruct-mlx-2Bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```