Hugging Face's logo

maia2000
/
ner-camembert_base

Safetensors
camembert
Model card Files
xet
 Community
maia2000 commited on
Commit
32211b1
·
verified ·
1 Parent(s): 3b89e4d

Upload NER model camembert_base

Browse files
Files changed (6) hide show
  1. config.json +58 -0
  2. label_mapping.json +32 -0
  3. model.safetensors +3 -0
  4. special_tokens_map.json +20 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +84 -0
config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "camembert-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": "B-ARR",
15
+ "1": "B-DEP",
16
+ "2": "B-MISC",
17
+ "3": "B-PER",
18
+ "4": "B-TEMP",
19
+ "5": "B-TRANSPORT",
20
+ "6": "I-ARR",
21
+ "7": "I-DEP",
22
+ "8": "I-MISC",
23
+ "9": "I-PER",
24
+ "10": "I-TEMP",
25
+ "11": "I-TRANSPORT",
26
+ "12": "O"
27
+ },
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": 3072,
30
+ "label2id": {
31
+ "B-ARR": 0,
32
+ "B-DEP": 1,
33
+ "B-MISC": 2,
34
+ "B-PER": 3,
35
+ "B-TEMP": 4,
36
+ "B-TRANSPORT": 5,
37
+ "I-ARR": 6,
38
+ "I-DEP": 7,
39
+ "I-MISC": 8,
40
+ "I-PER": 9,
41
+ "I-TEMP": 10,
42
+ "I-TRANSPORT": 11,
43
+ "O": 12
44
+ },
45
+ "layer_norm_eps": 1e-05,
46
+ "max_position_embeddings": 514,
47
+ "model_type": "camembert",
48
+ "num_attention_heads": 12,
49
+ "num_hidden_layers": 12,
50
+ "output_past": true,
51
+ "pad_token_id": 1,
52
+ "position_embedding_type": "absolute",
53
+ "torch_dtype": "float32",
54
+ "transformers_version": "4.44.1",
55
+ "type_vocab_size": 1,
56
+ "use_cache": true,
57
+ "vocab_size": 32005
58
+ }
label_mapping.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "label2id": {
3
+ "B-ARR": 0,
4
+ "B-DEP": 1,
5
+ "B-MISC": 2,
6
+ "B-PER": 3,
7
+ "B-TEMP": 4,
8
+ "B-TRANSPORT": 5,
9
+ "I-ARR": 6,
10
+ "I-DEP": 7,
11
+ "I-MISC": 8,
12
+ "I-PER": 9,
13
+ "I-TEMP": 10,
14
+ "I-TRANSPORT": 11,
15
+ "O": 12
16
+ },
17
+ "id2label": {
18
+ "0": "B-ARR",
19
+ "1": "B-DEP",
20
+ "2": "B-MISC",
21
+ "3": "B-PER",
22
+ "4": "B-TEMP",
23
+ "5": "B-TRANSPORT",
24
+ "6": "I-ARR",
25
+ "7": "I-DEP",
26
+ "8": "I-MISC",
27
+ "9": "I-PER",
28
+ "10": "I-TEMP",
29
+ "11": "I-TRANSPORT",
30
+ "12": "O"
31
+ }
32
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c836eff3be9c099405c29f9b473785866636b7ec576d5c7262b8f9465d7dd96d
3
+ size 440189348
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<s>NOTUSED",
4
+ "</s>NOTUSED",
5
+ "<unk>NOTUSED"
6
+ ],
7
+ "bos_token": "<s>",
8
+ "cls_token": "<s>",
9
+ "eos_token": "</s>",
10
+ "mask_token": {
11
+ "content": "<mask>",
12
+ "lstrip": true,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ "pad_token": "<pad>",
18
+ "sep_token": "</s>",
19
+ "unk_token": "<unk>"
20
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,84 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": true,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<s>NOTUSED",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<pad>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>NOTUSED",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "4": {
29
+ "content": "<unk>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "5": {
37
+ "content": "<s>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "6": {
45
+ "content": "</s>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "32004": {
53
+ "content": "<mask>",
54
+ "lstrip": true,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "32005": {
61
+ "content": "<unk>NOTUSED",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ }
68
+ },
69
+ "additional_special_tokens": [
70
+ "<s>NOTUSED",
71
+ "</s>NOTUSED",
72
+ "<unk>NOTUSED"
73
+ ],
74
+ "bos_token": "<s>",
75
+ "clean_up_tokenization_spaces": true,
76
+ "cls_token": "<s>",
77
+ "eos_token": "</s>",
78
+ "mask_token": "<mask>",
79
+ "model_max_length": 512,
80
+ "pad_token": "<pad>",
81
+ "sep_token": "</s>",
82
+ "tokenizer_class": "CamembertTokenizer",
83
+ "unk_token": "<unk>"
84
+ }