AshwinKM2005/github-duplicates-cross-encoder

1{2  "architectures": [3    "DebertaV2ForSequenceClassification"4  ],5  "attention_probs_dropout_prob": 0.1,6  "dtype": "bfloat16",7  "hidden_act": "gelu",8  "hidden_dropout_prob": 0.1,9  "hidden_size": 768,10  "id2label": {11    "0": "LABEL_0"12  },13  "initializer_range": 0.02,14  "intermediate_size": 3072,15  "label2id": {16    "LABEL_0": 017  },18  "layer_norm_eps": 1e-07,19  "legacy": true,20  "max_position_embeddings": 512,21  "max_relative_positions": -1,22  "model_type": "deberta-v2",23  "norm_rel_ebd": "layer_norm",24  "num_attention_heads": 12,25  "num_hidden_layers": 12,26  "pad_token_id": 0,27  "pooler_dropout": 0,28  "pooler_hidden_act": "gelu",29  "pooler_hidden_size": 768,30  "pos_att_type": [31    "p2c",32    "c2p"33  ],34  "position_biased_input": false,35  "position_buckets": 256,36  "relative_attention": true,37  "share_att_key": true,38  "transformers_version": "4.57.0",39  "type_vocab_size": 0,40  "vocab_size": 12810041}42