NeuronZero
commited on
Commit
•
2f443a2
1
Parent(s):
77e8de0
Upload 8 files
Browse files- added_tokens.json +3 -0
- config.json +205 -0
- model.safetensors +3 -0
- special_tokens_map.json +15 -0
- spm.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
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": "I-ADMINISTRATION",
|
15 |
+
"4": "B-ADMINISTRATION",
|
16 |
+
"5": "B-AGE",
|
17 |
+
"6": "I-AGE",
|
18 |
+
"7": "I-AREA",
|
19 |
+
"8": "B-AREA",
|
20 |
+
"9": "B-BIOLOGICAL_ATTRIBUTE",
|
21 |
+
"10": "I-BIOLOGICAL_ATTRIBUTE",
|
22 |
+
"11": "I-BIOLOGICAL_STRUCTURE",
|
23 |
+
"12": "B-BIOLOGICAL_STRUCTURE",
|
24 |
+
"13": "B-CLINICAL_EVENT",
|
25 |
+
"14": "I-CLINICAL_EVENT",
|
26 |
+
"15": "B-COLOR",
|
27 |
+
"16": "I-COLOR",
|
28 |
+
"17": "I-COREFERENCE",
|
29 |
+
"18": "B-COREFERENCE",
|
30 |
+
"19": "B-DATE",
|
31 |
+
"20": "I-DATE",
|
32 |
+
"21": "I-DETAILED_DESCRIPTION",
|
33 |
+
"22": "B-DETAILED_DESCRIPTION",
|
34 |
+
"23": "I-DIAGNOSTIC_PROCEDURE",
|
35 |
+
"24": "B-DIAGNOSTIC_PROCEDURE",
|
36 |
+
"25": "I-DISEASE_DISORDER",
|
37 |
+
"26": "B-DISEASE_DISORDER",
|
38 |
+
"27": "B-DISTANCE",
|
39 |
+
"28": "I-DISTANCE",
|
40 |
+
"29": "B-DOSAGE",
|
41 |
+
"30": "I-DOSAGE",
|
42 |
+
"31": "I-DURATION",
|
43 |
+
"32": "B-DURATION",
|
44 |
+
"33": "I-FAMILY_HISTORY",
|
45 |
+
"34": "B-FAMILY_HISTORY",
|
46 |
+
"35": "B-FREQUENCY",
|
47 |
+
"36": "I-FREQUENCY",
|
48 |
+
"37": "I-HEIGHT",
|
49 |
+
"38": "B-HEIGHT",
|
50 |
+
"39": "B-HISTORY",
|
51 |
+
"40": "I-HISTORY",
|
52 |
+
"41": "I-LAB_VALUE",
|
53 |
+
"42": "B-LAB_VALUE",
|
54 |
+
"43": "I-MASS",
|
55 |
+
"44": "B-MASS",
|
56 |
+
"45": "I-MEDICATION",
|
57 |
+
"46": "B-MEDICATION",
|
58 |
+
"47": "I-NONBIOLOGICAL_LOCATION",
|
59 |
+
"48": "B-NONBIOLOGICAL_LOCATION",
|
60 |
+
"49": "I-OCCUPATION",
|
61 |
+
"50": "B-OCCUPATION",
|
62 |
+
"51": "B-OTHER_ENTITY",
|
63 |
+
"52": "I-OTHER_ENTITY",
|
64 |
+
"53": "B-OTHER_EVENT",
|
65 |
+
"54": "I-OTHER_EVENT",
|
66 |
+
"55": "I-OUTCOME",
|
67 |
+
"56": "B-OUTCOME",
|
68 |
+
"57": "I-PERSONAL_BACKGROUND",
|
69 |
+
"58": "B-PERSONAL_BACKGROUND",
|
70 |
+
"59": "B-QUALITATIVE_CONCEPT",
|
71 |
+
"60": "I-QUALITATIVE_CONCEPT",
|
72 |
+
"61": "I-QUANTITATIVE_CONCEPT",
|
73 |
+
"62": "B-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": "I-TIME",
|
89 |
+
"78": "B-TIME",
|
90 |
+
"79": "B-VOLUME",
|
91 |
+
"80": "I-VOLUME",
|
92 |
+
"81": "I-WEIGHT",
|
93 |
+
"82": "B-WEIGHT"
|
94 |
+
},
|
95 |
+
"initializer_range": 0.02,
|
96 |
+
"intermediate_size": 3072,
|
97 |
+
"label2id": {
|
98 |
+
"B-ACTIVITY": 1,
|
99 |
+
"B-ADMINISTRATION": 4,
|
100 |
+
"B-AGE": 5,
|
101 |
+
"B-AREA": 8,
|
102 |
+
"B-BIOLOGICAL_ATTRIBUTE": 9,
|
103 |
+
"B-BIOLOGICAL_STRUCTURE": 12,
|
104 |
+
"B-CLINICAL_EVENT": 13,
|
105 |
+
"B-COLOR": 15,
|
106 |
+
"B-COREFERENCE": 18,
|
107 |
+
"B-DATE": 19,
|
108 |
+
"B-DETAILED_DESCRIPTION": 22,
|
109 |
+
"B-DIAGNOSTIC_PROCEDURE": 24,
|
110 |
+
"B-DISEASE_DISORDER": 26,
|
111 |
+
"B-DISTANCE": 27,
|
112 |
+
"B-DOSAGE": 29,
|
113 |
+
"B-DURATION": 32,
|
114 |
+
"B-FAMILY_HISTORY": 34,
|
115 |
+
"B-FREQUENCY": 35,
|
116 |
+
"B-HEIGHT": 38,
|
117 |
+
"B-HISTORY": 39,
|
118 |
+
"B-LAB_VALUE": 42,
|
119 |
+
"B-MASS": 44,
|
120 |
+
"B-MEDICATION": 46,
|
121 |
+
"B-NONBIOLOGICAL_LOCATION": 48,
|
122 |
+
"B-OCCUPATION": 50,
|
123 |
+
"B-OTHER_ENTITY": 51,
|
124 |
+
"B-OTHER_EVENT": 53,
|
125 |
+
"B-OUTCOME": 56,
|
126 |
+
"B-PERSONAL_BACKGROUND": 58,
|
127 |
+
"B-QUALITATIVE_CONCEPT": 59,
|
128 |
+
"B-QUANTITATIVE_CONCEPT": 62,
|
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": 78,
|
137 |
+
"B-VOLUME": 79,
|
138 |
+
"B-WEIGHT": 82,
|
139 |
+
"I-ACTIVITY": 2,
|
140 |
+
"I-ADMINISTRATION": 3,
|
141 |
+
"I-AGE": 6,
|
142 |
+
"I-AREA": 7,
|
143 |
+
"I-BIOLOGICAL_ATTRIBUTE": 10,
|
144 |
+
"I-BIOLOGICAL_STRUCTURE": 11,
|
145 |
+
"I-CLINICAL_EVENT": 14,
|
146 |
+
"I-COLOR": 16,
|
147 |
+
"I-COREFERENCE": 17,
|
148 |
+
"I-DATE": 20,
|
149 |
+
"I-DETAILED_DESCRIPTION": 21,
|
150 |
+
"I-DIAGNOSTIC_PROCEDURE": 23,
|
151 |
+
"I-DISEASE_DISORDER": 25,
|
152 |
+
"I-DISTANCE": 28,
|
153 |
+
"I-DOSAGE": 30,
|
154 |
+
"I-DURATION": 31,
|
155 |
+
"I-FAMILY_HISTORY": 33,
|
156 |
+
"I-FREQUENCY": 36,
|
157 |
+
"I-HEIGHT": 37,
|
158 |
+
"I-HISTORY": 40,
|
159 |
+
"I-LAB_VALUE": 41,
|
160 |
+
"I-MASS": 43,
|
161 |
+
"I-MEDICATION": 45,
|
162 |
+
"I-NONBIOLOGICAL_LOCATION": 47,
|
163 |
+
"I-OCCUPATION": 49,
|
164 |
+
"I-OTHER_ENTITY": 52,
|
165 |
+
"I-OTHER_EVENT": 54,
|
166 |
+
"I-OUTCOME": 55,
|
167 |
+
"I-PERSONAL_BACKGROUND": 57,
|
168 |
+
"I-QUALITATIVE_CONCEPT": 60,
|
169 |
+
"I-QUANTITATIVE_CONCEPT": 61,
|
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": 77,
|
178 |
+
"I-VOLUME": 80,
|
179 |
+
"I-WEIGHT": 81,
|
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": "4.37.0",
|
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 sha256:9fa0137fc2d0383aefa8cbb7dcce0e85ccc7f88290951419ac54a160343aaf7d
|
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 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d82257d8194d3d25a29011a6bfec613c3acf7495068de099fcd2d8f178a32419
|
3 |
+
size 4664
|