Qwen2.5-1.5B-8bit / README.md
prince-canuma's picture
9742ebbe95ab98f12847b4a1b3a5c6748dabda5eadd3cd9aae427964c470d63f
9af9de3 verified
|
raw
history blame
648 Bytes
---
language:
- en
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen2.5-1.5B/blob/main/LICENSE
pipeline_tag: text-generation
tags:
- mlx
---
# mlx-community/Qwen2.5-1.5B-8bit
The Model [mlx-community/Qwen2.5-1.5B-8bit](https://huggingface.co/mlx-community/Qwen2.5-1.5B-8bit) was converted to MLX format from [Qwen/Qwen2.5-1.5B](https://huggingface.co/Qwen/Qwen2.5-1.5B) 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/Qwen2.5-1.5B-8bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```