shraajan commited on
Commit
84bb4cb
·
verified ·
1 Parent(s): a7edd40

Upload 7 files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
config.json ADDED
@@ -0,0 +1,197 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/deberta-v3-base",
3
+ "architectures": [
4
+ "DebertaV2ForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "hidden_act": "gelu",
8
+ "hidden_dropout_prob": 0.1,
9
+ "hidden_size": 768,
10
+ "id2label": {
11
+ "0": "B-AB-NEG",
12
+ "1": "B-AB-NEU",
13
+ "2": "B-AB-POS",
14
+ "3": "B-AP-NEG",
15
+ "4": "B-AP-NEU",
16
+ "5": "B-AP-POS",
17
+ "6": "B-DU-NEG",
18
+ "7": "B-DU-NEU",
19
+ "8": "B-DU-POS",
20
+ "9": "B-EF-NEG",
21
+ "10": "B-EF-NEU",
22
+ "11": "B-EF-POS",
23
+ "12": "B-HY-NEG",
24
+ "13": "B-HY-NEU",
25
+ "14": "B-HY-POS",
26
+ "15": "B-PE-NEG",
27
+ "16": "B-PE-NEU",
28
+ "17": "B-PE-POS",
29
+ "18": "B-PK-NEG",
30
+ "19": "B-PK-NEU",
31
+ "20": "B-PK-POS",
32
+ "21": "B-QU-NEG",
33
+ "22": "B-QU-NEU",
34
+ "23": "B-QU-POS",
35
+ "24": "B-SC-NEG",
36
+ "25": "B-SC-NEU",
37
+ "26": "B-SC-POS",
38
+ "27": "B-SE-NEG",
39
+ "28": "B-SE-NEU",
40
+ "29": "B-SE-POS",
41
+ "30": "B-TX-NEG",
42
+ "31": "B-TX-NEU",
43
+ "32": "B-TX-POS",
44
+ "33": "B-VP-NEG",
45
+ "34": "B-VP-NEU",
46
+ "35": "B-VP-POS",
47
+ "36": "B_BP",
48
+ "37": "B_BR",
49
+ "38": "B_IN",
50
+ "39": "B_PT",
51
+ "40": "B_SW",
52
+ "41": "I-AB-NEG",
53
+ "42": "I-AB-NEU",
54
+ "43": "I-AB-POS",
55
+ "44": "I-AP-NEG",
56
+ "45": "I-AP-NEU",
57
+ "46": "I-AP-POS",
58
+ "47": "I-DU-NEG",
59
+ "48": "I-DU-NEU",
60
+ "49": "I-DU-POS",
61
+ "50": "I-EF-NEG",
62
+ "51": "I-EF-NEU",
63
+ "52": "I-EF-POS",
64
+ "53": "I-HY-NEG",
65
+ "54": "I-HY-POS",
66
+ "55": "I-PE-NEG",
67
+ "56": "I-PE-POS",
68
+ "57": "I-PK-NEG",
69
+ "58": "I-PK-POS",
70
+ "59": "I-QU-NEG",
71
+ "60": "I-QU-POS",
72
+ "61": "I-SC-NEG",
73
+ "62": "I-SC-NEU",
74
+ "63": "I-SC-POS",
75
+ "64": "I-SE-NEG",
76
+ "65": "I-SE-NEU",
77
+ "66": "I-SE-POS",
78
+ "67": "I-TX-NEG",
79
+ "68": "I-TX-NEU",
80
+ "69": "I-TX-POS",
81
+ "70": "I-VP-NEG",
82
+ "71": "I-VP-NEU",
83
+ "72": "I-VP-POS",
84
+ "73": "I_BP",
85
+ "74": "I_BR",
86
+ "75": "I_IN",
87
+ "76": "I_PT",
88
+ "77": "I_SW",
89
+ "78": "O"
90
+ },
91
+ "initializer_range": 0.02,
92
+ "intermediate_size": 3072,
93
+ "label2id": {
94
+ "B-AB-NEG": 0,
95
+ "B-AB-NEU": 1,
96
+ "B-AB-POS": 2,
97
+ "B-AP-NEG": 3,
98
+ "B-AP-NEU": 4,
99
+ "B-AP-POS": 5,
100
+ "B-DU-NEG": 6,
101
+ "B-DU-NEU": 7,
102
+ "B-DU-POS": 8,
103
+ "B-EF-NEG": 9,
104
+ "B-EF-NEU": 10,
105
+ "B-EF-POS": 11,
106
+ "B-HY-NEG": 12,
107
+ "B-HY-NEU": 13,
108
+ "B-HY-POS": 14,
109
+ "B-PE-NEG": 15,
110
+ "B-PE-NEU": 16,
111
+ "B-PE-POS": 17,
112
+ "B-PK-NEG": 18,
113
+ "B-PK-NEU": 19,
114
+ "B-PK-POS": 20,
115
+ "B-QU-NEG": 21,
116
+ "B-QU-NEU": 22,
117
+ "B-QU-POS": 23,
118
+ "B-SC-NEG": 24,
119
+ "B-SC-NEU": 25,
120
+ "B-SC-POS": 26,
121
+ "B-SE-NEG": 27,
122
+ "B-SE-NEU": 28,
123
+ "B-SE-POS": 29,
124
+ "B-TX-NEG": 30,
125
+ "B-TX-NEU": 31,
126
+ "B-TX-POS": 32,
127
+ "B-VP-NEG": 33,
128
+ "B-VP-NEU": 34,
129
+ "B-VP-POS": 35,
130
+ "B_BP": 36,
131
+ "B_BR": 37,
132
+ "B_IN": 38,
133
+ "B_PT": 39,
134
+ "B_SW": 40,
135
+ "I-AB-NEG": 41,
136
+ "I-AB-NEU": 42,
137
+ "I-AB-POS": 43,
138
+ "I-AP-NEG": 44,
139
+ "I-AP-NEU": 45,
140
+ "I-AP-POS": 46,
141
+ "I-DU-NEG": 47,
142
+ "I-DU-NEU": 48,
143
+ "I-DU-POS": 49,
144
+ "I-EF-NEG": 50,
145
+ "I-EF-NEU": 51,
146
+ "I-EF-POS": 52,
147
+ "I-HY-NEG": 53,
148
+ "I-HY-POS": 54,
149
+ "I-PE-NEG": 55,
150
+ "I-PE-POS": 56,
151
+ "I-PK-NEG": 57,
152
+ "I-PK-POS": 58,
153
+ "I-QU-NEG": 59,
154
+ "I-QU-POS": 60,
155
+ "I-SC-NEG": 61,
156
+ "I-SC-NEU": 62,
157
+ "I-SC-POS": 63,
158
+ "I-SE-NEG": 64,
159
+ "I-SE-NEU": 65,
160
+ "I-SE-POS": 66,
161
+ "I-TX-NEG": 67,
162
+ "I-TX-NEU": 68,
163
+ "I-TX-POS": 69,
164
+ "I-VP-NEG": 70,
165
+ "I-VP-NEU": 71,
166
+ "I-VP-POS": 72,
167
+ "I_BP": 73,
168
+ "I_BR": 74,
169
+ "I_IN": 75,
170
+ "I_PT": 76,
171
+ "I_SW": 77,
172
+ "O": 78
173
+ },
174
+ "layer_norm_eps": 1e-07,
175
+ "max_position_embeddings": 512,
176
+ "max_relative_positions": -1,
177
+ "model_type": "deberta-v2",
178
+ "norm_rel_ebd": "layer_norm",
179
+ "num_attention_heads": 12,
180
+ "num_hidden_layers": 12,
181
+ "pad_token_id": 0,
182
+ "pooler_dropout": 0,
183
+ "pooler_hidden_act": "gelu",
184
+ "pooler_hidden_size": 768,
185
+ "pos_att_type": [
186
+ "p2c",
187
+ "c2p"
188
+ ],
189
+ "position_biased_input": false,
190
+ "position_buckets": 256,
191
+ "relative_attention": true,
192
+ "share_att_key": true,
193
+ "torch_dtype": "float32",
194
+ "transformers_version": "4.35.2",
195
+ "type_vocab_size": 0,
196
+ "vocab_size": 128100
197
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a695d9c68c1e03d2eddc65fc80425b54bf1617be7860da1b8f32953cb159a1ee
3
+ size 735593596
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "[CLS]",
3
+ "cls_token": "[CLS]",
4
+ "eos_token": "[SEP]",
5
+ "mask_token": "[MASK]",
6
+ "pad_token": "[PAD]",
7
+ "sep_token": "[SEP]",
8
+ "unk_token": {
9
+ "content": "[UNK]",
10
+ "lstrip": false,
11
+ "normalized": true,
12
+ "rstrip": false,
13
+ "single_word": false
14
+ }
15
+ }
spm.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
3
+ size 2464616
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "[CLS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "[SEP]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "[UNK]",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128000": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "[CLS]",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "[CLS]",
47
+ "do_lower_case": false,
48
+ "eos_token": "[SEP]",
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 1000000000000000019884624838656,
51
+ "pad_token": "[PAD]",
52
+ "sep_token": "[SEP]",
53
+ "sp_model_kwargs": {},
54
+ "split_by_punct": false,
55
+ "tokenizer_class": "DebertaV2Tokenizer",
56
+ "unk_token": "[UNK]",
57
+ "vocab_type": "spm"
58
+ }