Instructions to use cubeus/Behemoth-123B-v1.2-Q8-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use cubeus/Behemoth-123B-v1.2-Q8-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Behemoth-123B-v1.2-Q8-mlx cubeus/Behemoth-123B-v1.2-Q8-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
Upload model-00015-of-00026.safetensors with huggingface_hub
Browse files
model-00015-of-00026.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96c4783074f62066993b7dd92eccef49ba76d6ccd36cb305b359fd5ec6aa2679
|
| 3 |
+
size 5134034634
|