Upload 7 files
Browse files- config.json +171 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +57 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
@@ -0,0 +1,171 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "model/hin/bert/bert_hin_bi",
|
3 |
+
"architectures": [
|
4 |
+
"BertForTokenClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 768,
|
11 |
+
"id2label": {
|
12 |
+
"0": "CC",
|
13 |
+
"1": "CCS",
|
14 |
+
"2": "CC_CCS_CCS",
|
15 |
+
"3": "CD",
|
16 |
+
"4": "DEM",
|
17 |
+
"5": "DT",
|
18 |
+
"6": "EX",
|
19 |
+
"7": "FW",
|
20 |
+
"8": "IN",
|
21 |
+
"9": "INTF",
|
22 |
+
"10": "JJ",
|
23 |
+
"11": "JJR",
|
24 |
+
"12": "JJS",
|
25 |
+
"13": "LS",
|
26 |
+
"14": "MD",
|
27 |
+
"15": "NEG",
|
28 |
+
"16": "NN",
|
29 |
+
"17": "NNP",
|
30 |
+
"18": "NNPS",
|
31 |
+
"19": "NNS",
|
32 |
+
"20": "NN_NNP",
|
33 |
+
"21": "NP",
|
34 |
+
"22": "PDT",
|
35 |
+
"23": "POS",
|
36 |
+
"24": "PPS",
|
37 |
+
"25": "PR",
|
38 |
+
"26": "PRP",
|
39 |
+
"27": "PRP$",
|
40 |
+
"28": "PRP_PRP",
|
41 |
+
"29": "PR_INTF",
|
42 |
+
"30": "PR_PR",
|
43 |
+
"31": "PSP",
|
44 |
+
"32": "PUNC",
|
45 |
+
"33": "QC",
|
46 |
+
"34": "QF",
|
47 |
+
"35": "QT",
|
48 |
+
"36": "QTF",
|
49 |
+
"37": "QT_QRF",
|
50 |
+
"38": "QT_QT",
|
51 |
+
"39": "QT_QTC",
|
52 |
+
"40": "RB",
|
53 |
+
"41": "RBR",
|
54 |
+
"42": "RBS",
|
55 |
+
"43": "RD_ECE",
|
56 |
+
"44": "RD_SYM",
|
57 |
+
"45": "RD_PUNC",
|
58 |
+
"46": "RP",
|
59 |
+
"47": "RP_ING",
|
60 |
+
"48": "RP_NSG",
|
61 |
+
"49": "SYM",
|
62 |
+
"50": "TO",
|
63 |
+
"51": "UH",
|
64 |
+
"52": "VB",
|
65 |
+
"53": "VBD",
|
66 |
+
"54": "VBG",
|
67 |
+
"55": "VBN",
|
68 |
+
"56": "VBP",
|
69 |
+
"57": "VBZ",
|
70 |
+
"58": "V_AUX",
|
71 |
+
"59": "V_VAUX",
|
72 |
+
"60": "V_VM",
|
73 |
+
"61": "V_VM_INF",
|
74 |
+
"62": "V_VM_VG",
|
75 |
+
"63": "V_VM_VMF",
|
76 |
+
"64": "V_VN_VNF",
|
77 |
+
"65": "WDT",
|
78 |
+
"66": "WP",
|
79 |
+
"67": "WP$",
|
80 |
+
"68": "WRB",
|
81 |
+
"69": "Wh-Word",
|
82 |
+
"70": "[PAD]"
|
83 |
+
},
|
84 |
+
"initializer_range": 0.02,
|
85 |
+
"intermediate_size": 3072,
|
86 |
+
"label2id": {
|
87 |
+
"CC": 0,
|
88 |
+
"CCS": 1,
|
89 |
+
"CC_CCS_CCS": 2,
|
90 |
+
"CD": 3,
|
91 |
+
"DEM": 4,
|
92 |
+
"DT": 5,
|
93 |
+
"EX": 6,
|
94 |
+
"FW": 7,
|
95 |
+
"IN": 8,
|
96 |
+
"INTF": 9,
|
97 |
+
"JJ": 10,
|
98 |
+
"JJR": 11,
|
99 |
+
"JJS": 12,
|
100 |
+
"LS": 13,
|
101 |
+
"MD": 14,
|
102 |
+
"NEG": 15,
|
103 |
+
"NN": 16,
|
104 |
+
"NNP": 17,
|
105 |
+
"NNPS": 18,
|
106 |
+
"NNS": 19,
|
107 |
+
"NN_NNP": 20,
|
108 |
+
"NP": 21,
|
109 |
+
"PDT": 22,
|
110 |
+
"POS": 23,
|
111 |
+
"PPS": 24,
|
112 |
+
"PR": 25,
|
113 |
+
"PRP": 26,
|
114 |
+
"PRP$": 27,
|
115 |
+
"PRP_PRP": 28,
|
116 |
+
"PR_INTF": 29,
|
117 |
+
"PR_PR": 30,
|
118 |
+
"PSP": 31,
|
119 |
+
"PUNC": 32,
|
120 |
+
"QC": 33,
|
121 |
+
"QF": 34,
|
122 |
+
"QT": 35,
|
123 |
+
"QTF": 36,
|
124 |
+
"QT_QRF": 37,
|
125 |
+
"QT_QT": 38,
|
126 |
+
"QT_QTC": 39,
|
127 |
+
"RB": 40,
|
128 |
+
"RBR": 41,
|
129 |
+
"RBS": 42,
|
130 |
+
"RD_ECE": 43,
|
131 |
+
"RD_PUNC": 45,
|
132 |
+
"RD_SYM": 44,
|
133 |
+
"RP": 46,
|
134 |
+
"RP_ING": 47,
|
135 |
+
"RP_NSG": 48,
|
136 |
+
"SYM": 49,
|
137 |
+
"TO": 50,
|
138 |
+
"UH": 51,
|
139 |
+
"VB": 52,
|
140 |
+
"VBD": 53,
|
141 |
+
"VBG": 54,
|
142 |
+
"VBN": 55,
|
143 |
+
"VBP": 56,
|
144 |
+
"VBZ": 57,
|
145 |
+
"V_AUX": 58,
|
146 |
+
"V_VAUX": 59,
|
147 |
+
"V_VM": 60,
|
148 |
+
"V_VM_INF": 61,
|
149 |
+
"V_VM_VG": 62,
|
150 |
+
"V_VM_VMF": 63,
|
151 |
+
"V_VN_VNF": 64,
|
152 |
+
"WDT": 65,
|
153 |
+
"WP": 66,
|
154 |
+
"WP$": 67,
|
155 |
+
"WRB": 68,
|
156 |
+
"Wh-Word": 69,
|
157 |
+
"[PAD]": 70
|
158 |
+
},
|
159 |
+
"layer_norm_eps": 1e-12,
|
160 |
+
"max_position_embeddings": 256,
|
161 |
+
"model_type": "bert",
|
162 |
+
"num_attention_heads": 12,
|
163 |
+
"num_hidden_layers": 12,
|
164 |
+
"pad_token_id": 0,
|
165 |
+
"position_embedding_type": "absolute",
|
166 |
+
"torch_dtype": "float32",
|
167 |
+
"transformers_version": "4.35.0",
|
168 |
+
"type_vocab_size": 2,
|
169 |
+
"use_cache": true,
|
170 |
+
"vocab_size": 52000
|
171 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b81b74a5e718d5108e721b4ec17cbedb25dff733cd99aebe97d85f3bcfc03a6d
|
3 |
+
size 501002324
|
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 1000000000000000019884624838656,
|
50 |
+
"never_split": null,
|
51 |
+
"pad_token": "[PAD]",
|
52 |
+
"sep_token": "[SEP]",
|
53 |
+
"strip_accents": false,
|
54 |
+
"tokenize_chinese_chars": true,
|
55 |
+
"tokenizer_class": "BertTokenizer",
|
56 |
+
"unk_token": "[UNK]"
|
57 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:900cde996da2baae7554a81c274d41ff4701f803f55891942dc36c7d44bc7c0b
|
3 |
+
size 4143
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|