venkatd commited on
Commit
7ba9ecd
1 Parent(s): c545726

Upload 7 files

Browse files
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[MASK]": 128000
3
+ }
config.json ADDED
@@ -0,0 +1,205 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "O",
12
+ "1": "B-Activity",
13
+ "2": "I-Activity",
14
+ "3": "B-Administration",
15
+ "4": "I-Administration",
16
+ "5": "B-Age",
17
+ "6": "I-Age",
18
+ "7": "B-Area",
19
+ "8": "I-Area",
20
+ "9": "B-Biological_attribute",
21
+ "10": "I-Biological_attribute",
22
+ "11": "B-Biological_structure",
23
+ "12": "I-Biological_structure",
24
+ "13": "B-Clinical_event",
25
+ "14": "I-Clinical_event",
26
+ "15": "B-Color",
27
+ "16": "I-Color",
28
+ "17": "B-Coreference",
29
+ "18": "I-Coreference",
30
+ "19": "B-Date",
31
+ "20": "I-Date",
32
+ "21": "B-Detailed_description",
33
+ "22": "I-Detailed_description",
34
+ "23": "B-Diagnostic_procedure",
35
+ "24": "I-Diagnostic_procedure",
36
+ "25": "B-Disease_disorder",
37
+ "26": "I-Disease_disorder",
38
+ "27": "B-Distance",
39
+ "28": "I-Distance",
40
+ "29": "B-Dosage",
41
+ "30": "I-Dosage",
42
+ "31": "B-Duration",
43
+ "32": "I-Duration",
44
+ "33": "B-Family_history",
45
+ "34": "I-Family_history",
46
+ "35": "B-Frequency",
47
+ "36": "I-Frequency",
48
+ "37": "B-Height",
49
+ "38": "I-Height",
50
+ "39": "B-History",
51
+ "40": "I-History",
52
+ "41": "B-Lab_value",
53
+ "42": "I-Lab_value",
54
+ "43": "B-Mass",
55
+ "44": "I-Mass",
56
+ "45": "B-Medication",
57
+ "46": "I-Medication",
58
+ "47": "B-Nonbiological_location",
59
+ "48": "I-Nonbiological_location",
60
+ "49": "B-Occupation",
61
+ "50": "I-Occupation",
62
+ "51": "B-Other_entity",
63
+ "52": "I-Other_entity",
64
+ "53": "B-Other_event",
65
+ "54": "I-Other_event",
66
+ "55": "B-Outcome",
67
+ "56": "I-Outcome",
68
+ "57": "B-Personal_background",
69
+ "58": "I-Personal_background",
70
+ "59": "B-Qualitative_concept",
71
+ "60": "I-Qualitative_concept",
72
+ "61": "B-Quantitative_concept",
73
+ "62": "I-Quantitative_concept",
74
+ "63": "B-Severity",
75
+ "64": "I-Severity",
76
+ "65": "B-Sex",
77
+ "66": "I-Sex",
78
+ "67": "B-Shape",
79
+ "68": "I-Shape",
80
+ "69": "B-Sign_symptom",
81
+ "70": "I-Sign_symptom",
82
+ "71": "B-Subject",
83
+ "72": "I-Subject",
84
+ "73": "B-Texture",
85
+ "74": "I-Texture",
86
+ "75": "B-Therapeutic_procedure",
87
+ "76": "I-Therapeutic_procedure",
88
+ "77": "B-Time",
89
+ "78": "I-Time",
90
+ "79": "B-Volume",
91
+ "80": "I-Volume",
92
+ "81": "B-Weight",
93
+ "82": "I-Weight"
94
+ },
95
+ "initializer_range": 0.02,
96
+ "intermediate_size": 3072,
97
+ "label2id": {
98
+ "B-Activity": 1,
99
+ "B-Administration": 3,
100
+ "B-Age": 5,
101
+ "B-Area": 7,
102
+ "B-Biological_attribute": 9,
103
+ "B-Biological_structure": 11,
104
+ "B-Clinical_event": 13,
105
+ "B-Color": 15,
106
+ "B-Coreference": 17,
107
+ "B-Date": 19,
108
+ "B-Detailed_description": 21,
109
+ "B-Diagnostic_procedure": 23,
110
+ "B-Disease_disorder": 25,
111
+ "B-Distance": 27,
112
+ "B-Dosage": 29,
113
+ "B-Duration": 31,
114
+ "B-Family_history": 33,
115
+ "B-Frequency": 35,
116
+ "B-Height": 37,
117
+ "B-History": 39,
118
+ "B-Lab_value": 41,
119
+ "B-Mass": 43,
120
+ "B-Medication": 45,
121
+ "B-Nonbiological_location": 47,
122
+ "B-Occupation": 49,
123
+ "B-Other_entity": 51,
124
+ "B-Other_event": 53,
125
+ "B-Outcome": 55,
126
+ "B-Personal_background": 57,
127
+ "B-Qualitative_concept": 59,
128
+ "B-Quantitative_concept": 61,
129
+ "B-Severity": 63,
130
+ "B-Sex": 65,
131
+ "B-Shape": 67,
132
+ "B-Sign_symptom": 69,
133
+ "B-Subject": 71,
134
+ "B-Texture": 73,
135
+ "B-Therapeutic_procedure": 75,
136
+ "B-Time": 77,
137
+ "B-Volume": 79,
138
+ "B-Weight": 81,
139
+ "I-Activity": 2,
140
+ "I-Administration": 4,
141
+ "I-Age": 6,
142
+ "I-Area": 8,
143
+ "I-Biological_attribute": 10,
144
+ "I-Biological_structure": 12,
145
+ "I-Clinical_event": 14,
146
+ "I-Color": 16,
147
+ "I-Coreference": 18,
148
+ "I-Date": 20,
149
+ "I-Detailed_description": 22,
150
+ "I-Diagnostic_procedure": 24,
151
+ "I-Disease_disorder": 26,
152
+ "I-Distance": 28,
153
+ "I-Dosage": 30,
154
+ "I-Duration": 32,
155
+ "I-Family_history": 34,
156
+ "I-Frequency": 36,
157
+ "I-Height": 38,
158
+ "I-History": 40,
159
+ "I-Lab_value": 42,
160
+ "I-Mass": 44,
161
+ "I-Medication": 46,
162
+ "I-Nonbiological_location": 48,
163
+ "I-Occupation": 50,
164
+ "I-Other_entity": 52,
165
+ "I-Other_event": 54,
166
+ "I-Outcome": 56,
167
+ "I-Personal_background": 58,
168
+ "I-Qualitative_concept": 60,
169
+ "I-Quantitative_concept": 62,
170
+ "I-Severity": 64,
171
+ "I-Sex": 66,
172
+ "I-Shape": 68,
173
+ "I-Sign_symptom": 70,
174
+ "I-Subject": 72,
175
+ "I-Texture": 74,
176
+ "I-Therapeutic_procedure": 76,
177
+ "I-Time": 78,
178
+ "I-Volume": 80,
179
+ "I-Weight": 82,
180
+ "O": 0
181
+ },
182
+ "layer_norm_eps": 1e-07,
183
+ "max_position_embeddings": 512,
184
+ "max_relative_positions": -1,
185
+ "model_type": "deberta-v2",
186
+ "norm_rel_ebd": "layer_norm",
187
+ "num_attention_heads": 12,
188
+ "num_hidden_layers": 12,
189
+ "pad_token_id": 0,
190
+ "pooler_dropout": 0,
191
+ "pooler_hidden_act": "gelu",
192
+ "pooler_hidden_size": 768,
193
+ "pos_att_type": [
194
+ "p2c",
195
+ "c2p"
196
+ ],
197
+ "position_biased_input": false,
198
+ "position_buckets": 256,
199
+ "relative_attention": true,
200
+ "share_att_key": true,
201
+ "torch_dtype": "float32",
202
+ "transformers_version": "4.41.2",
203
+ "type_vocab_size": 0,
204
+ "vocab_size": 128100
205
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d08ccc361af0a22193167f6d4237f62c9adaef7b0dc4dafb00d48f84b46e8e5a
3
+ size 735605900
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
+ }