Hugging Face's logo

medkit
/
CamemBert-Bio-Generalized

Token Classification
Transformers
Safetensors
camembert
Inference Endpoints
Model card Files Community
Thibeb commited on
Commit
7e32d4e
•
1 Parent(s): eabfb25

Upload 8 files

Browse files
Files changed (8) hide show
  1. config.json +74 -0
  2. model.safetensors +3 -0
  3. optimizer.pt +3 -0
  4. sentencepiece.bpe.model +3 -0
  5. special_tokens_map.json +19 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +74 -0
  8. trainer_config.yml +11 -0
config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "almanach/camembert-bio-base",
3
+ "architectures": [
4
+ "CamembertForTokenClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 5,
8
+ "classifier_dropout": null,
9
+ "eos_token_id": 6,
10
+ "hidden_act": "gelu",
11
+ "hidden_dropout_prob": 0.1,
12
+ "hidden_size": 768,
13
+ "id2label": {
14
+ "0": "O",
15
+ "1": "B-ANAT",
16
+ "2": "I-ANAT",
17
+ "3": "B-CHEM",
18
+ "4": "I-CHEM",
19
+ "5": "B-DEVI",
20
+ "6": "I-DEVI",
21
+ "7": "B-DISO",
22
+ "8": "I-DISO",
23
+ "9": "B-GEOG",
24
+ "10": "I-GEOG",
25
+ "11": "B-LIVB",
26
+ "12": "I-LIVB",
27
+ "13": "B-OBJC",
28
+ "14": "I-OBJC",
29
+ "15": "B-PHEN",
30
+ "16": "I-PHEN",
31
+ "17": "B-PHYS",
32
+ "18": "I-PHYS",
33
+ "19": "B-PROC",
34
+ "20": "I-PROC"
35
+ },
36
+ "initializer_range": 0.02,
37
+ "intermediate_size": 3072,
38
+ "label2id": {
39
+ "B-ANAT": 1,
40
+ "B-CHEM": 3,
41
+ "B-DEVI": 5,
42
+ "B-DISO": 7,
43
+ "B-GEOG": 9,
44
+ "B-LIVB": 11,
45
+ "B-OBJC": 13,
46
+ "B-PHEN": 15,
47
+ "B-PHYS": 17,
48
+ "B-PROC": 19,
49
+ "I-ANAT": 2,
50
+ "I-CHEM": 4,
51
+ "I-DEVI": 6,
52
+ "I-DISO": 8,
53
+ "I-GEOG": 10,
54
+ "I-LIVB": 12,
55
+ "I-OBJC": 14,
56
+ "I-PHEN": 16,
57
+ "I-PHYS": 18,
58
+ "I-PROC": 20,
59
+ "O": 0
60
+ },
61
+ "layer_norm_eps": 1e-05,
62
+ "max_position_embeddings": 514,
63
+ "model_type": "camembert",
64
+ "num_attention_heads": 12,
65
+ "num_hidden_layers": 12,
66
+ "output_past": true,
67
+ "pad_token_id": 1,
68
+ "position_embedding_type": "absolute",
69
+ "torch_dtype": "float32",
70
+ "transformers_version": "4.35.2",
71
+ "type_vocab_size": 1,
72
+ "use_cache": true,
73
+ "vocab_size": 32005
74
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9edc9e29a3cecdc944d12c167f4ac2fdc9eb41027f38cbfca9d81119fcf27e1
3
+ size 440213956
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1f0701e216e018316020924309f188783c1e2dae9745eec60b541b52ae7e5d1
3
+ size 880546362
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:988bc5a00281c6d210a5d34bd143d0363741a432fefe741bf71e61b1869d4314
3
+ size 810912
special_tokens_map.json ADDED
@@ -0,0 +1,19 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "</s>NOTUSED"
5
+ ],
6
+ "bos_token": "<s>",
7
+ "cls_token": "<s>",
8
+ "eos_token": "</s>",
9
+ "mask_token": {
10
+ "content": "<mask>",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<pad>",
17
+ "sep_token": "</s>",
18
+ "unk_token": "<unk>"
19
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>NOTUSED",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>NOTUSED",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "4": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "5": {
36
+ "content": "<s>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "6": {
44
+ "content": "</s>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "32004": {
52
+ "content": "<mask>",
53
+ "lstrip": true,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "additional_special_tokens": [
61
+ "<s>NOTUSED",
62
+ "</s>NOTUSED"
63
+ ],
64
+ "bos_token": "<s>",
65
+ "clean_up_tokenization_spaces": true,
66
+ "cls_token": "<s>",
67
+ "eos_token": "</s>",
68
+ "mask_token": "<mask>",
69
+ "model_max_length": 512,
70
+ "pad_token": "<pad>",
71
+ "sep_token": "</s>",
72
+ "tokenizer_class": "CamembertTokenizer",
73
+ "unk_token": "<unk>"
74
+ }
trainer_config.yml ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ learning_rate: 5.0e-05
2
+ nb_training_epochs: 10
3
+ dataloader_nb_workers: 0
4
+ batch_size: 16
5
+ seed: null
6
+ gradient_accumulation_steps: 1
7
+ do_metrics_in_training: false
8
+ metric_to_track_lr: loss
9
+ checkpoint_period: 1
10
+ checkpoint_metric: loss
11
+ minimize_checkpoint_metric: true