CARROT-LLM-Routing/Cost

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  },28  "initializer_range": 0.02,29  "intermediate_size": 3072,30  "label2id": {31    "LABEL_0": 0,32    "LABEL_1": 1,33    "LABEL_10": 10,34    "LABEL_11": 11,35    "LABEL_12": 12,36    "LABEL_2": 2,37    "LABEL_3": 3,38    "LABEL_4": 4,39    "LABEL_5": 5,40    "LABEL_6": 6,41    "LABEL_7": 7,42    "LABEL_8": 8,43    "LABEL_9": 944  },45  "layer_norm_eps": 1e-05,46  "max_position_embeddings": 514,47  "model_type": "roberta",48  "num_attention_heads": 12,49  "num_hidden_layers": 12,50  "pad_token_id": 1,51  "position_embedding_type": "absolute",52  "problem_type": "regression",53  "torch_dtype": "float32",54  "transformers_version": "4.48.1",55  "type_vocab_size": 1,56  "use_cache": true,57  "vocab_size": 5026558}59