Instructions to use pepoo20/working with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use pepoo20/working with PEFT:
Task type is invalid.
- Notebooks
- Google Colab
- Kaggle
Download adapter_config.json from pepoo20/working: direct link, hf CLI and curl.
- Browser
- Download file 565 Bytes
-
https://huggingface.co/pepoo20/working/resolve/main/adapter_config.json
- Command line
-
hf download hf://pepoo20/working/adapter_config.json
-
curl -L -o adapter_config.json https://huggingface.co/pepoo20/working/resolve/main/adapter_config.json
565 Bytes
| { | |
| "auto_mapping": { | |
| "base_model_class": "Wav2Vec2ForCTC", | |
| "parent_library": "transformers.models.wav2vec2.modeling_wav2vec2" | |
| }, | |
| "base_model_name_or_path": "Umong/wav2vec2-large-mms-1b-bengali", | |
| "bias": "none", | |
| "fan_in_fan_out": false, | |
| "inference_mode": true, | |
| "init_lora_weights": true, | |
| "layers_pattern": null, | |
| "layers_to_transform": null, | |
| "lora_alpha": 64, | |
| "lora_dropout": 0.05, | |
| "modules_to_save": null, | |
| "peft_type": "LORA", | |
| "r": 32, | |
| "revision": null, | |
| "target_modules": [ | |
| "q_proj", | |
| "v_proj" | |
| ], | |
| "task_type": null | |
| } |