yanghaojin's picture
Upload folder using huggingface_hub
5d83870 verified
|
raw
history blame
567 Bytes
---
license: apache-2.0
tags:
- mlx
---
# GreenBitAI/Qwen-1.5-7B-layer-mix-bpw-3.0-mlx
This quantized low-bit model was converted to MLX format from [`GreenBitAI/Qwen-1.5-7B-layer-mix-bpw-3.0`]().
Refer to the [original model card](https://huggingface.co/GreenBitAI/Qwen-1.5-7B-layer-mix-bpw-3.0) for more details on the model.
## Use with mlx
```bash
pip install gbx-lm
```
```python
from gbx_lm import load, generate
model, tokenizer = load("GreenBitAI/Qwen-1.5-7B-layer-mix-bpw-3.0-mlx")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```