{ "_name_or_path": "/gpfs/home/jc3821/kaggle/microsoft-deberta-v3-large", "architectures": [ "DebertaV2ForSequenceClassification" ], "attention_probs_dropout_prob": 0.007, "hidden_act": "gelu", "hidden_dropout_prob": 0.007, "hidden_size": 1024, "id2label": { "0": "LABEL_0" }, "initializer_range": 0.02, "intermediate_size": 4096, "label2id": { "LABEL_0": 0 }, "layer_norm_eps": 1e-07, "max_position_embeddings": 512, "max_relative_positions": -1, "model_type": "deberta-v2", "norm_rel_ebd": "layer_norm", "num_attention_heads": 16, "num_hidden_layers": 24, "pad_token_id": 0, "pooler_dropout": 0, "pooler_hidden_act": "gelu", "pooler_hidden_size": 1024, "pos_att_type": [ "p2c", "c2p" ], "position_biased_input": false, "position_buckets": 256, "problem_type": "regression", "relative_attention": true, "share_att_key": true, "torch_dtype": "float32", "transformers_version": "4.32.1", "type_vocab_size": 0, "vocab_size": 128100 }