Instructions to use runanywhere/whisper_medium_4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use runanywhere/whisper_medium_4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir whisper_medium_4bit runanywhere/whisper_medium_4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Add root config.json for download tracking
Browse files- config.json +17 -0
config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"n_mels": 80,
|
| 3 |
+
"n_audio_ctx": 1500,
|
| 4 |
+
"n_audio_state": 1024,
|
| 5 |
+
"n_audio_head": 16,
|
| 6 |
+
"n_audio_layer": 24,
|
| 7 |
+
"n_vocab": 51865,
|
| 8 |
+
"n_text_ctx": 448,
|
| 9 |
+
"n_text_state": 1024,
|
| 10 |
+
"n_text_head": 16,
|
| 11 |
+
"n_text_layer": 24,
|
| 12 |
+
"quantization": {
|
| 13 |
+
"group_size": 64,
|
| 14 |
+
"bits": 4
|
| 15 |
+
},
|
| 16 |
+
"model_type": "whisper"
|
| 17 |
+
}
|