| { | |
| "_name_or_path": "checkpoint/bert_ND_router/checkpoint-38814", | |
| "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": "gpt-3.5-turbo", | |
| "1": "gpt-4" | |
| }, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 3072, | |
| "label2id": { | |
| "gpt-3.5-turbo": 0, | |
| "gpt-4": 1 | |
| }, | |
| "layer_norm_eps": 1e-12, | |
| "max_position_embeddings": 512, | |
| "model_type": "bert", | |
| "num_attention_heads": 12, | |
| "num_hidden_layers": 12, | |
| "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", | |
| "pretraining_tp": 1, | |
| "problem_type": "single_label_classification", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.30.0", | |
| "type_vocab_size": 2, | |
| "use_cache": true, | |
| "vocab_size": 119547 | |
| } | |