Instructions to use Daizee/X-Ray_Alpha-mlx-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Daizee/X-Ray_Alpha-mlx-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download Daizee/X-Ray_Alpha-mlx-4bit --local-dir X-Ray_Alpha-mlx-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Delete generation_config.json
Browse files- generation_config.json +0 -12
generation_config.json
DELETED
|
@@ -1,12 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_from_model_config": true,
|
| 3 |
-
"bos_token_id": 2,
|
| 4 |
-
"cache_implementation": "hybrid",
|
| 5 |
-
"do_sample": true,
|
| 6 |
-
"eos_token_id": [
|
| 7 |
-
1,
|
| 8 |
-
106
|
| 9 |
-
],
|
| 10 |
-
"pad_token_id": 0,
|
| 11 |
-
"transformers_version": "4.50.0.dev0"
|
| 12 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|