k2rks's picture
63f5ec41dcda4b77dd77f419c1f12de81a3fd0f72ccbe64d10d30eacdcc2b14c
982b5e2 verified
|
raw
history blame
706 Bytes
---
license: other
license_name: deepseek-license
license_link: LICENSE
tags:
- mlx
---
# mlx-community/DeepSeek-Coder-V2-Lite-Instruct-8bit
The Model [mlx-community/DeepSeek-Coder-V2-Lite-Instruct-8bit](https://huggingface.co/mlx-community/DeepSeek-Coder-V2-Lite-Instruct-8bit) was converted to MLX format from [deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct](https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct) using mlx-lm version **0.18.1**.
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/DeepSeek-Coder-V2-Lite-Instruct-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```