StanfordSCALE/tutor_talkmoves_roberta_large_classifier

1{2  "architectures": [3    "RobertaModel"4  ],5  "attention_probs_dropout_prob": 0.1,6  "bos_token_id": 0,7  "classifier_dropout": null,8  "eos_token_id": 2,9  "hidden_act": "gelu",10  "hidden_dropout_prob": 0.1,11  "hidden_size": 1024,12  "id2label": {13    "0": "2 - Pressing for Accuracy or Reasoning",14    "1": "1 - Classroom Management",15    "2": "0 - None",16    "3": "3 - Restating or Revoicing"17  },18  "initializer_range": 0.02,19  "intermediate_size": 4096,20  "label2id": {21    "0 - None": 2,22    "1 - Classroom Management": 1,23    "2 - Pressing for Accuracy or Reasoning": 0,24    "3 - Restating or Revoicing": 325  },26  "layer_norm_eps": 1e-05,27  "max_position_embeddings": 514,28  "model_type": "roberta",29  "num_attention_heads": 16,30  "num_hidden_layers": 24,31  "pad_token_id": 1,32  "position_embedding_type": "absolute",33  "problem_type": "single_label_classification",34  "torch_dtype": "float32",35  "transformers_version": "4.55.2",36  "type_vocab_size": 1,37  "use_cache": true,38  "vocab_size": 5026739}40