deberta-foodex2-coder / config.json
alecocc's picture
Training in progress, step 200
1bfd5ed verified
{
"_name_or_path": "microsoft/deberta-v3-small",
"architectures": [
"DebertaV2ForSequenceClassification"
],
"attention_probs_dropout_prob": 0.1,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "F01",
"1": "F02",
"2": "F03",
"3": "F04",
"4": "F06",
"5": "F07",
"6": "F08",
"7": "F09",
"8": "F10",
"9": "F11",
"10": "F12",
"11": "F15",
"12": "F17",
"13": "F18",
"14": "F19",
"15": "F20",
"16": "F21",
"17": "F22",
"18": "F23",
"19": "F24",
"20": "F25",
"21": "F26",
"22": "F27",
"23": "F28",
"24": "F31",
"25": "F33"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"F01": 0,
"F02": 1,
"F03": 2,
"F04": 3,
"F06": 4,
"F07": 5,
"F08": 6,
"F09": 7,
"F10": 8,
"F11": 9,
"F12": 10,
"F15": 11,
"F17": 12,
"F18": 13,
"F19": 14,
"F20": 15,
"F21": 16,
"F22": 17,
"F23": 18,
"F24": 19,
"F25": 20,
"F26": 21,
"F27": 22,
"F28": 23,
"F31": 24,
"F33": 25
},
"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": 6,
"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,
"problem_type": "multi_label_classification",
"relative_attention": true,
"share_att_key": true,
"torch_dtype": "float32",
"transformers_version": "4.48.3",
"type_vocab_size": 0,
"vocab_size": 128100
}