|
--- |
|
language: |
|
- en |
|
license: other |
|
tags: |
|
- pretrained |
|
- moe |
|
- mlx |
|
license_name: tongyi-qianwen |
|
license_link: https://huggingface.co./Qwen/Qwen1.5-MoE-A2.7B/blob/main/LICENSE |
|
pipeline_tag: text-generation |
|
--- |
|
|
|
# mlx-community/Qwen1.5-MoE-A2.7B-4bit |
|
This model was converted to MLX format from [`Qwen/Qwen1.5-MoE-A2.7B`](https://huggingface.co./Qwen/Qwen1.5-MoE-A2.7B) using mlx-lm version version [d661440](https://github.com/ml-explore/mlx-examples/commit/d661440dbb8e1970fadad79c5061e786fe1c54ca). |
|
|
|
Model added by [Prince Canuma](https://twitter.com/Prince_Canuma). |
|
|
|
Refer to the [original model card](https://huggingface.co./Qwen/Qwen1.5-MoE-A2.7B) for more details on the model. |
|
## Use with mlx |
|
|
|
```bash |
|
pip install mlx-lm |
|
``` |
|
|
|
```python |
|
from mlx_lm import load, generate |
|
|
|
model, tokenizer = load("mlx-community/Qwen1.5-MoE-A2.7B-4bit") |
|
response = generate(model, tokenizer, prompt="Write a story about Einstein", verbose=True) |
|
``` |
|
|
