| { | |
| "_name_or_path": "carles-undergrad-thesis/distillbert-tasb-en-id-mmarco-knowledge-distillation", | |
| "activation": "gelu", | |
| "architectures": [ | |
| "DistilBertModel" | |
| ], | |
| "attention_dropout": 0.1, | |
| "dim": 768, | |
| "dropout": 0.1, | |
| "hidden_dim": 3072, | |
| "initializer_range": 0.02, | |
| "max_position_embeddings": 512, | |
| "model_type": "distilbert", | |
| "n_heads": 12, | |
| "n_layers": 6, | |
| "output_past": true, | |
| "pad_token_id": 0, | |
| "qa_dropout": 0.1, | |
| "seq_classif_dropout": 0.2, | |
| "sinusoidal_pos_embds": false, | |
| "tie_weights_": true, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.34.0", | |
| "vocab_size": 119547 | |
| } | |