| { |
| "alpha_pattern": {}, |
| "auto_mapping": { |
| "base_model_class": "HubertForSequenceClassification", |
| "parent_library": "transformers.models.hubert.modeling_hubert" |
| }, |
| "base_model_name_or_path": "ntu-spml/distilhubert", |
| "bias": "none", |
| "corda_config": null, |
| "eva_config": null, |
| "exclude_modules": null, |
| "fan_in_fan_out": false, |
| "inference_mode": true, |
| "init_lora_weights": true, |
| "layer_replication": null, |
| "layers_pattern": null, |
| "layers_to_transform": null, |
| "loftq_config": {}, |
| "lora_alpha": 32, |
| "lora_bias": false, |
| "lora_dropout": 0.5, |
| "megatron_config": null, |
| "megatron_core": "megatron.core", |
| "modules_to_save": null, |
| "peft_type": "LORA", |
| "r": 8, |
| "rank_pattern": {}, |
| "revision": null, |
| "target_modules": [ |
| "hubert.feature_projection.projection", |
| "classifier", |
| "hubert.encoder.layers.0.attention.v_proj", |
| "hubert.encoder.layers.1.feed_forward.intermediate_dense", |
| "hubert.encoder.layers.0.feed_forward.output_dense", |
| "hubert.encoder.layers.1.attention.out_proj", |
| "hubert.encoder.layers.0.attention.q_proj", |
| "hubert.encoder.layers.0.feed_forward.intermediate_dense", |
| "hubert.encoder.layers.1.attention.q_proj", |
| "hubert.encoder.layers.1.feed_forward.output_dense", |
| "projector", |
| "hubert.encoder.layers.0.attention.k_proj", |
| "hubert.encoder.layers.0.attention.out_proj", |
| "hubert.encoder.layers.1.attention.v_proj", |
| "hubert.encoder.layers.1.attention.k_proj" |
| ], |
| "task_type": null, |
| "trainable_token_indices": null, |
| "use_dora": false, |
| "use_rslora": false |
| } |
