{ "activation": "gelu", "architectures": [ "DistilBertForSequenceClassification" ], "attention_dropout": 0.1, "bos_token_id": 0, "dim": 768, "dropout": 0.1, "eos_token_ids": 0, "finetuning_task": "mnli", "hidden_dim": 3072, "id2label": { "0": "contradiction", "1": "entailment", "2": "neutral" }, "initializer_range": 0.02, "label2id": { "contradiction": "0", "entailment": "1", "neutral": "2" }, "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, "vocab_size": 30522 }