CARROT-LLM-Routing/costo3

1{2  "_name_or_path": "roberta-base",3  "architectures": [4    "RobertaForSequenceClassification"5  ],6  "attention_probs_dropout_prob": 0.1,7  "bos_token_id": 0,8  "classifier_dropout": null,9  "eos_token_id": 2,10  "hidden_act": "gelu",11  "hidden_dropout_prob": 0.1,12  "hidden_size": 768,13  "id2label": {14    "0": "LABEL_0",15    "1": "LABEL_1",16    "2": "LABEL_2",17    "3": "LABEL_3",18    "4": "LABEL_4",19    "5": "LABEL_5",20    "6": "LABEL_6",21    "7": "LABEL_7",22    "8": "LABEL_8",23    "9": "LABEL_9",24    "10": "LABEL_10",25    "11": "LABEL_11",26    "12": "LABEL_12",27    "13": "LABEL_13"28  },29  "initializer_range": 0.02,30  "intermediate_size": 3072,31  "label2id": {32    "LABEL_0": 0,33    "LABEL_1": 1,34    "LABEL_10": 10,35    "LABEL_11": 11,36    "LABEL_12": 12,37    "LABEL_13": 13,38    "LABEL_2": 2,39    "LABEL_3": 3,40    "LABEL_4": 4,41    "LABEL_5": 5,42    "LABEL_6": 6,43    "LABEL_7": 7,44    "LABEL_8": 8,45    "LABEL_9": 946  },47  "layer_norm_eps": 1e-05,48  "max_position_embeddings": 514,49  "model_type": "roberta",50  "num_attention_heads": 12,51  "num_hidden_layers": 12,52  "pad_token_id": 1,53  "position_embedding_type": "absolute",54  "problem_type": "regression",55  "torch_dtype": "float32",56  "transformers_version": "4.48.1",57  "type_vocab_size": 1,58  "use_cache": true,59  "vocab_size": 5026560}61