{ "_name_or_path": "microsoft/deberta-v3-base", "architectures": [ "DebertaV2ForTokenClassification" ], "attention_probs_dropout_prob": 0.1, "first_token": false, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "id2label": { "\"": 0, "#": 2, "$": 3, "''": 1, "(": 4, ")": 5, ",": 6, ".": 7, ":": 8, "CC": 10, "CD": 11, "DT": 12, "EX": 13, "FW": 14, "IN": 15, "JJ": 16, "JJR": 17, "JJS": 18, "LS": 19, "MD": 20, "NN": 21, "NNP": 22, "NNPS": 23, "NNS": 24, "NN|SYM": 25, "PDT": 26, "POS": 27, "PRP": 28, "PRP$": 29, "RB": 30, "RBR": 31, "RBS": 32, "RP": 33, "SYM": 34, "TO": 35, "UH": 36, "VB": 37, "VBD": 38, "VBG": 39, "VBN": 40, "VBP": 41, "VBZ": 42, "WDT": 43, "WP": 44, "WP$": 45, "WRB": 46, "``": 9 }, "initializer_range": 0.02, "intermediate_size": 3072, "label2id": { "\"": 0, "#": 2, "$": 3, "''": 1, "(": 4, ")": 5, ",": 6, ".": 7, ":": 8, "CC": 10, "CD": 11, "DT": 12, "EX": 13, "FW": 14, "IN": 15, "JJ": 16, "JJR": 17, "JJS": 18, "LS": 19, "MD": 20, "NN": 21, "NNP": 22, "NNPS": 23, "NNS": 24, "NN|SYM": 25, "PDT": 26, "POS": 27, "PRP": 28, "PRP$": 29, "RB": 30, "RBR": 31, "RBS": 32, "RP": 33, "SYM": 34, "TO": 35, "UH": 36, "VB": 37, "VBD": 38, "VBG": 39, "VBN": 40, "VBP": 41, "VBZ": 42, "WDT": 43, "WP": 44, "WP$": 45, "WRB": 46, "``": 9 }, "layer_norm_eps": 1e-07, "loss": "ce", "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": "float32", "transformers_version": "4.26.1", "type_vocab_size": 0, "vocab_size": 128100 }