Instructions to use mohan007/pi05-mlx-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mohan007/pi05-mlx-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir pi05-mlx-4bit mohan007/pi05-mlx-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
Add 4-bit quantized MLX weights for pi0.5
Browse files- pi05_mlx_4bit.npz +3 -0
pi05_mlx_4bit.npz
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff8bf110ed61224bd3d1500244787c84043bae38d673777e91023c256f1771bc
|
| 3 |
+
size 2838608420
|