MLX
Safetensors
ONNX
English
qwen3
decision-model
candidate-scorer
calibration
selective-prediction
on-device
4-bit precision
Instructions to use alexzhang0118/Decily-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use alexzhang0118/Decily-MLX-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download alexzhang0118/Decily-MLX-4bit --local-dir Decily-MLX-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Upload assets/decily-1.7b-banner.png with huggingface_hub
Browse files- .gitattributes +1 -0
- assets/decily-1.7b-banner.png +3 -0
.gitattributes
CHANGED
|
@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
assets/decily-1.7b-banner.png filter=lfs diff=lfs merge=lfs -text
|
assets/decily-1.7b-banner.png
ADDED
|
Git LFS Details
|