Instructions to use kruatech/studio-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use kruatech/studio-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download kruatech/studio-mlx --local-dir studio-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Remove tokenizer/generation_config.json: it came in because --tokenizer pointed at the t5gemma model folder, and the weights are already in weights/text_encoder.safetensors
Browse files
stable-audio-3-medium/tokenizer/generation_config.json
DELETED
|
@@ -1,10 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"_from_model_config": true,
|
| 3 |
-
"bos_token_id": 2,
|
| 4 |
-
"eos_token_id": [
|
| 5 |
-
1,
|
| 6 |
-
107
|
| 7 |
-
],
|
| 8 |
-
"pad_token_id": 0,
|
| 9 |
-
"transformers_version": "4.53.0.dev0"
|
| 10 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|