| { | |
| "architectures": [ | |
| "BertForSequenceClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.4, | |
| "directionality": "bidi", | |
| "do_sample": true, | |
| "eos_token_ids": null, | |
| "gradient_checkpointing": false, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.3, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1", | |
| "2": "LABEL_2" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1, | |
| "LABEL_2": 2 | |
| }, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 512, | |
| "model_type": "bert", | |
| "num_attention_heads": 12, | |
| "num_beams": 500, | |
| "num_hidden_layers": 12, | |
| "output_past": true, | |
| "pooler_fc_size": 768, | |
| "pooler_num_attention_heads": 12, | |
| "pooler_num_fc_layers": 3, | |
| "pooler_size_per_head": 128, | |
| "pooler_type": "first_token_transform", | |
| "repetition_penalty": 5, | |
| "type_vocab_size": 2, | |
| "vocab_size": 119547 | |
| } | |