MLX
Safetensors
llama
Yi-1.5-34B-4bit / README.md
prince-canuma's picture
Update README.md
2ef9128 verified
|
raw
history blame
588 Bytes
---
license: apache-2.0
tags:
- mlx
---
# mlx-community/Yi-1.5-34B-4bit
The Model [mlx-community/Yi-1.5-34B-4bit](https://huggingface.co/mlx-community/Yi-1.5-34B-4bit) was converted to MLX format from [01-ai/Yi-1.5-34B](https://huggingface.co/01-ai/Yi-1.5-34B) using mlx-lm version **0.13.0**.
Model added by [Prince Canuma](https://twitter.com/Prince_Canuma).
## Use with mlx
```bash
pip install mlx-lm
```
```python
from mlx_lm import load, generate
model, tokenizer = load("mlx-community/Yi-1.5-34B-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```