| { | |
| "_name_or_path": "hfl/rbt3", | |
| "architectures": [ | |
| "BertForSequenceClassification" | |
| ], | |
| "attention_probs_dropout_prob": 0.1, | |
| "classifier_dropout": null, | |
| "directionality": "bidi", | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.1, | |
| "hidden_size": 768, | |
| "id2label": { | |
| "0": "\u8ba1\u7b97\u673a\u67b6\u6784", | |
| "1": "\u7b97\u6cd5\u4e0e\u6570\u636e\u7ed3\u6784", | |
| "2": "\u7f16\u7a0b\u8bed\u8a00\u4e0e\u7f16\u8bd1\u5668", | |
| "3": "\u6570\u5b66\u77e5\u8bc6", | |
| "4": "\u64cd\u4f5c\u7cfb\u7edf", | |
| "5": "\u8ba1\u7b97\u673a\u7f51\u7edc", | |
| "6": "\u6570\u636e\u5e93", | |
| "7": "\u4eba\u5de5\u667a\u80fd", | |
| "8": "\u8f6f\u4ef6\u5de5\u7a0b" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "label2id": { | |
| "\u4eba\u5de5\u667a\u80fd": 7, | |
| "\u64cd\u4f5c\u7cfb\u7edf": 4, | |
| "\u6570\u5b66\u77e5\u8bc6": 3, | |
| "\u6570\u636e\u5e93": 6, | |
| "\u7b97\u6cd5\u4e0e\u6570\u636e\u7ed3\u6784": 1, | |
| "\u7f16\u7a0b\u8bed\u8a00\u4e0e\u7f16\u8bd1\u5668": 2, | |
| "\u8ba1\u7b97\u673a\u67b6\u6784": 0, | |
| "\u8ba1\u7b97\u673a\u7f51\u7edc": 5, | |
| "\u8f6f\u4ef6\u5de5\u7a0b": 8 | |
| }, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 512, | |
| "model_type": "bert", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 3, | |
| "output_past": true, | |
| "pad_token_id": 0, | |
| "pooler_fc_size": 768, | |
| "pooler_num_attention_heads": 12, | |
| "pooler_num_fc_layers": 3, | |
| "pooler_size_per_head": 128, | |
| "pooler_type": "first_token_transform", | |
| "position_embedding_type": "absolute", | |
| "problem_type": "single_label_classification", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.18.0", | |
| "type_vocab_size": 2, | |
| "use_cache": true, | |
| "vocab_size": 21128 | |
| } | |