{ "_name_or_path": "/scratch/hvp2011/hvp/tp/er_icml2026/checkpoints/ER/arm-7B-4gpu-bmax1.0-bmin0.5-r0.7-lr5e-5-emafalse-a0.05-t1.0/global_step_57/router/huggingface", "architectures": [ "DebertaV2ForSequenceClassification" ], "attention_probs_dropout_prob": 0.1, "classifier_dropout": 0.0, "dtype": "float32", "hidden_act": "gelu", "hidden_dropout": "0", "hidden_dropout_prob": 0.1, "hidden_size": 768, "id2label": { "0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2", "3": "LABEL_3" }, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "ANSWER": 0, "CODE": 3, "COT": 1, "LONG_COT": 2 }, "layer_norm_eps": 1e-07, "legacy": true, "max_position_embeddings": 512, "max_relative_positions": -1, "model_type": "deberta-v2", "norm_rel_ebd": "layer_norm", "num_attention_heads": 12, "num_hidden_layers": 12, "pad_token_id": 0, "pooler_dropout": 0, "pooler_hidden_act": "gelu", "pooler_hidden_size": 768, "pos_att_type": [ "p2c", "c2p" ], "position_biased_input": false, "position_buckets": 256, "relative_attention": true, "share_att_key": true, "torch_dtype": "bfloat16", "transformers_version": "4.49.0", "type_vocab_size": 0, "vocab_size": 128100 }