Misha24-10 commited on
Commit
94ce3c0
1 Parent(s): bf1389e

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
config.json ADDED
@@ -0,0 +1,178 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./xlm-roberta-large",
3
+ "architectures": [
4
+ "XLMRobertaForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 1024,
13
+ "id2label": {
14
+ "0": "B-Disease",
15
+ "1": "I-Disease",
16
+ "2": "B-Symptom",
17
+ "3": "I-Symptom",
18
+ "4": "B-AnatomicalStructure",
19
+ "5": "I-AnatomicalStructure",
20
+ "6": "B-MedicalProcedure",
21
+ "7": "I-MedicalProcedure",
22
+ "8": "B-Medication/Vaccine",
23
+ "9": "I-Medication/Vaccine",
24
+ "10": "B-OtherPROD",
25
+ "11": "I-OtherPROD",
26
+ "12": "B-Drink",
27
+ "13": "I-Drink",
28
+ "14": "B-Food",
29
+ "15": "I-Food",
30
+ "16": "B-Vehicle",
31
+ "17": "I-Vehicle",
32
+ "18": "B-Clothing",
33
+ "19": "I-Clothing",
34
+ "20": "B-OtherPER",
35
+ "21": "I-OtherPER",
36
+ "22": "B-SportsManager",
37
+ "23": "I-SportsManager",
38
+ "24": "B-Cleric",
39
+ "25": "I-Cleric",
40
+ "26": "B-Politician",
41
+ "27": "I-Politician",
42
+ "28": "B-Athlete",
43
+ "29": "I-Athlete",
44
+ "30": "B-Artist",
45
+ "31": "I-Artist",
46
+ "32": "B-Scientist",
47
+ "33": "I-Scientist",
48
+ "34": "B-ORG",
49
+ "35": "I-ORG",
50
+ "36": "B-TechCorp",
51
+ "37": "I-TechCorp",
52
+ "38": "B-CarManufacturer",
53
+ "39": "I-CarManufacturer",
54
+ "40": "B-SportsGRP",
55
+ "41": "I-SportsGRP",
56
+ "42": "B-AerospaceManufacturer",
57
+ "43": "I-AerospaceManufacturer",
58
+ "44": "B-OtherCorp",
59
+ "45": "I-OtherCorp",
60
+ "46": "B-PrivateCorp",
61
+ "47": "I-PrivateCorp",
62
+ "48": "B-PublicCorp",
63
+ "49": "I-PublicCorp",
64
+ "50": "B-MusicalGRP",
65
+ "51": "I-MusicalGRP",
66
+ "52": "B-OtherCW",
67
+ "53": "I-OtherCW",
68
+ "54": "B-Software",
69
+ "55": "I-Software",
70
+ "56": "B-ArtWork",
71
+ "57": "I-ArtWork",
72
+ "58": "B-WrittenWork",
73
+ "59": "I-WrittenWork",
74
+ "60": "B-MusicalWork",
75
+ "61": "I-MusicalWork",
76
+ "62": "B-VisualWork",
77
+ "63": "I-VisualWork",
78
+ "64": "B-Station",
79
+ "65": "I-Station",
80
+ "66": "B-HumanSettlement",
81
+ "67": "I-HumanSettlement",
82
+ "68": "B-OtherLOC",
83
+ "69": "I-OtherLOC",
84
+ "70": "B-Facility",
85
+ "71": "I-Facility",
86
+ "72": "O"
87
+ },
88
+ "initializer_range": 0.02,
89
+ "intermediate_size": 4096,
90
+ "label2id": {
91
+ "B-AerospaceManufacturer": 42,
92
+ "B-AnatomicalStructure": 4,
93
+ "B-ArtWork": 56,
94
+ "B-Artist": 30,
95
+ "B-Athlete": 28,
96
+ "B-CarManufacturer": 38,
97
+ "B-Cleric": 24,
98
+ "B-Clothing": 18,
99
+ "B-Disease": 0,
100
+ "B-Drink": 12,
101
+ "B-Facility": 70,
102
+ "B-Food": 14,
103
+ "B-HumanSettlement": 66,
104
+ "B-MedicalProcedure": 6,
105
+ "B-Medication/Vaccine": 8,
106
+ "B-MusicalGRP": 50,
107
+ "B-MusicalWork": 60,
108
+ "B-ORG": 34,
109
+ "B-OtherCW": 52,
110
+ "B-OtherCorp": 44,
111
+ "B-OtherLOC": 68,
112
+ "B-OtherPER": 20,
113
+ "B-OtherPROD": 10,
114
+ "B-Politician": 26,
115
+ "B-PrivateCorp": 46,
116
+ "B-PublicCorp": 48,
117
+ "B-Scientist": 32,
118
+ "B-Software": 54,
119
+ "B-SportsGRP": 40,
120
+ "B-SportsManager": 22,
121
+ "B-Station": 64,
122
+ "B-Symptom": 2,
123
+ "B-TechCorp": 36,
124
+ "B-Vehicle": 16,
125
+ "B-VisualWork": 62,
126
+ "B-WrittenWork": 58,
127
+ "I-AerospaceManufacturer": 43,
128
+ "I-AnatomicalStructure": 5,
129
+ "I-ArtWork": 57,
130
+ "I-Artist": 31,
131
+ "I-Athlete": 29,
132
+ "I-CarManufacturer": 39,
133
+ "I-Cleric": 25,
134
+ "I-Clothing": 19,
135
+ "I-Disease": 1,
136
+ "I-Drink": 13,
137
+ "I-Facility": 71,
138
+ "I-Food": 15,
139
+ "I-HumanSettlement": 67,
140
+ "I-MedicalProcedure": 7,
141
+ "I-Medication/Vaccine": 9,
142
+ "I-MusicalGRP": 51,
143
+ "I-MusicalWork": 61,
144
+ "I-ORG": 35,
145
+ "I-OtherCW": 53,
146
+ "I-OtherCorp": 45,
147
+ "I-OtherLOC": 69,
148
+ "I-OtherPER": 21,
149
+ "I-OtherPROD": 11,
150
+ "I-Politician": 27,
151
+ "I-PrivateCorp": 47,
152
+ "I-PublicCorp": 49,
153
+ "I-Scientist": 33,
154
+ "I-Software": 55,
155
+ "I-SportsGRP": 41,
156
+ "I-SportsManager": 23,
157
+ "I-Station": 65,
158
+ "I-Symptom": 3,
159
+ "I-TechCorp": 37,
160
+ "I-Vehicle": 17,
161
+ "I-VisualWork": 63,
162
+ "I-WrittenWork": 59,
163
+ "O": 72
164
+ },
165
+ "layer_norm_eps": 1e-05,
166
+ "max_position_embeddings": 514,
167
+ "model_type": "xlm-roberta",
168
+ "num_attention_heads": 16,
169
+ "num_hidden_layers": 24,
170
+ "output_past": true,
171
+ "pad_token_id": 1,
172
+ "position_embedding_type": "absolute",
173
+ "torch_dtype": "float32",
174
+ "transformers_version": "4.26.1",
175
+ "type_vocab_size": 1,
176
+ "use_cache": true,
177
+ "vocab_size": 250002
178
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d284d5c0b1a7e06b6b1202dcba133e55cb4825214fd3dba9fe97b30ed3355516
3
+ size 2235799153
special_tokens_map.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eac3be632196404b59b7147df6fc1ee638cf6748c920bfb5e31357180cad7147
3
+ size 17082925
tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "__type": "AddedToken",
7
+ "content": "<mask>",
8
+ "lstrip": true,
9
+ "normalized": true,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "model_max_length": 1000000000000000019884624838656,
14
+ "name_or_path": "./xlm-roberta-large",
15
+ "pad_token": "<pad>",
16
+ "sep_token": "</s>",
17
+ "special_tokens_map_file": null,
18
+ "tokenizer_class": "XLMRobertaTokenizer",
19
+ "unk_token": "<unk>"
20
+ }