k2rks's picture
ab2fd6b3a2f182ad74e16f578b30078efcb83fb53ba76682405514bc77913833
35e3c59 verified
|
raw
history blame
583 Bytes
---
library_name: transformers
license: apache-2.0
tags:
- mlx
---
# mlx-community/Yi-Coder-9B-Chat-4bit
The Model [mlx-community/Yi-Coder-9B-Chat-4bit](https://huggingface.co/mlx-community/Yi-Coder-9B-Chat-4bit) was converted to MLX format from [01-ai/Yi-Coder-9B-Chat](https://huggingface.co/01-ai/Yi-Coder-9B-Chat) 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/Yi-Coder-9B-Chat-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```