{ "activation": "gelu", "architectures": [ "DistilBertForMaskedLM" ], "attention_dropout": 0.1, "bos_token_id": 0, "dim": 768, "do_sample": false, "dropout": 0.1, "eos_token_ids": 0, "finetuning_task": null, "hidden_dim": 3072, "id2label": { "0": "LABEL_0", "1": "LABEL_1" }, "initializer_range": 0.02, "is_decoder": false, "label2id": { "LABEL_0": 0, "LABEL_1": 1 }, "length_penalty": 1.0, "max_length": 20, "max_position_embeddings": 512, "model_type": "distilbert", "n_heads": 12, "n_layers": 6, "num_beams": 1, "num_labels": 2, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_past": true, "pad_token_id": 0, "pruned_heads": {}, "qa_dropout": 0.1, "repetition_penalty": 1.0, "seq_classif_dropout": 0.2, "sinusoidal_pos_embds": false, "temperature": 1.0, "tie_weights_": true, "top_k": 50, "top_p": 1.0, "torchscript": false, "use_bfloat16": false, "vocab_size": 28996 }