bengali_pos_v1_500000 / config.json
mHossain's picture
Training in progress, epoch 1
9ecd90c
raw
history blame
2.11 kB
{
"_name_or_path": "mHossain/bengali_pos_v1_400000",
"architectures": [
"ElectraForTokenClassification"
],
"attention_probs_dropout_prob": 0.1,
"classifier_dropout": null,
"embedding_size": 768,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"id2label": {
"0": "ADD",
"1": "AFX",
"2": "CC",
"3": "CD",
"4": "DT",
"5": "EX",
"6": "FW",
"7": "HYPH",
"8": "IN",
"9": "JJ",
"10": "JJR",
"11": "JJS",
"12": "LS",
"13": "MD",
"14": "NFP",
"15": "NN",
"16": "NNP",
"17": "NNPS",
"18": "NNS",
"19": "PDT",
"20": "POS",
"21": "PRP",
"22": "PRP$",
"23": "RB",
"24": "RBR",
"25": "RBS",
"26": "RP",
"27": "SYM",
"28": "TO",
"29": "UH",
"30": "VB",
"31": "VBD",
"32": "VBG",
"33": "VBN",
"34": "VBP",
"35": "VBZ",
"36": "WDT",
"37": "WP",
"38": "WP$",
"39": "WRB",
"40": "XX"
},
"initializer_range": 0.02,
"intermediate_size": 3072,
"label2id": {
"ADD": 0,
"AFX": 1,
"CC": 2,
"CD": 3,
"DT": 4,
"EX": 5,
"FW": 6,
"HYPH": 7,
"IN": 8,
"JJ": 9,
"JJR": 10,
"JJS": 11,
"LS": 12,
"MD": 13,
"NFP": 14,
"NN": 15,
"NNP": 16,
"NNPS": 17,
"NNS": 18,
"PDT": 19,
"POS": 20,
"PRP": 21,
"PRP$": 22,
"RB": 23,
"RBR": 24,
"RBS": 25,
"RP": 26,
"SYM": 27,
"TO": 28,
"UH": 29,
"VB": 30,
"VBD": 31,
"VBG": 32,
"VBN": 33,
"VBP": 34,
"VBZ": 35,
"WDT": 36,
"WP": 37,
"WP$": 38,
"WRB": 39,
"XX": 40
},
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "electra",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 0,
"position_embedding_type": "absolute",
"summary_activation": "gelu",
"summary_last_dropout": 0.1,
"summary_type": "first",
"summary_use_proj": true,
"torch_dtype": "float32",
"transformers_version": "4.35.2",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 32000
}