Hugging Face's logo

irenema
/
model_fr

Text Classification
Transformers
TensorBoard
Safetensors
bert
Inference Endpoints
Model card Files Metrics Community
irenema commited on
Commit
8fa9f55
•
1 Parent(s): bb66e15

Training in progress, epoch 1

Browse files
Files changed (6) hide show
  1. config.json +8 -11
  2. model.safetensors +2 -2
  3. special_tokens_map.json +5 -18
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +21 -46
  6. vocab.txt +0 -0
config.json CHANGED
@@ -1,12 +1,10 @@
1
  {
2
- "_name_or_path": "camembert-base",
3
  "architectures": [
4
- "CamembertForSequenceClassification"
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": 0.3,
12
  "hidden_size": 768,
@@ -26,18 +24,17 @@
26
  "S": 3,
27
  "T": 4
28
  },
29
- "layer_norm_eps": 1e-05,
30
- "max_position_embeddings": 514,
31
- "model_type": "camembert",
32
  "num_attention_heads": 12,
33
  "num_hidden_layers": 12,
34
- "output_past": true,
35
- "pad_token_id": 1,
36
  "position_embedding_type": "absolute",
37
  "problem_type": "single_label_classification",
38
  "torch_dtype": "float32",
39
  "transformers_version": "4.37.0.dev0",
40
- "type_vocab_size": 1,
41
  "use_cache": true,
42
- "vocab_size": 32005
43
  }
 
1
  {
2
+ "_name_or_path": "dbmdz/bert-base-italian-cased",
3
  "architectures": [
4
+ "BertForSequenceClassification"
5
  ],
6
  "attention_probs_dropout_prob": 0.1,
 
7
  "classifier_dropout": null,
 
8
  "hidden_act": "gelu",
9
  "hidden_dropout_prob": 0.3,
10
  "hidden_size": 768,
 
24
  "S": 3,
25
  "T": 4
26
  },
27
+ "layer_norm_eps": 1e-12,
28
+ "max_position_embeddings": 512,
29
+ "model_type": "bert",
30
  "num_attention_heads": 12,
31
  "num_hidden_layers": 12,
32
+ "pad_token_id": 0,
 
33
  "position_embedding_type": "absolute",
34
  "problem_type": "single_label_classification",
35
  "torch_dtype": "float32",
36
  "transformers_version": "4.37.0.dev0",
37
+ "type_vocab_size": 2,
38
  "use_cache": true,
39
+ "vocab_size": 31102
40
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8afb52cf2f3f4ce7d2883141ba9bd54331c78210a0ff2ab310303e864deecf94
3
- size 442527332
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce1af137184a124eeb6ad7d16b6f7bce4c90db2df2059b036081b208baf8c1aa
3
+ size 439749636
special_tokens_map.json CHANGED
@@ -1,20 +1,7 @@
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
  }
 
1
  {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,63 +1,39 @@
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
- "32005": {
60
- "content": "<unk>NOTUSED",
61
  "lstrip": false,
62
  "normalized": false,
63
  "rstrip": false,
@@ -65,19 +41,18 @@
65
  "special": true
66
  }
67
  },
68
- "additional_special_tokens": [
69
- "<s>NOTUSED",
70
- "</s>NOTUSED",
71
- "<unk>NOTUSED"
72
- ],
73
- "bos_token": "<s>",
74
  "clean_up_tokenization_spaces": true,
75
- "cls_token": "<s>",
76
- "eos_token": "</s>",
77
- "mask_token": "<mask>",
 
 
78
  "model_max_length": 512,
79
- "pad_token": "<pad>",
80
- "sep_token": "</s>",
81
- "tokenizer_class": "CamembertTokenizer",
82
- "unk_token": "<unk>"
 
 
 
83
  }
 
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
+ "101": {
12
+ "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "102": {
20
+ "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "103": {
28
+ "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "104": {
36
+ "content": "[MASK]",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
37
  "lstrip": false,
38
  "normalized": false,
39
  "rstrip": false,
 
41
  "special": true
42
  }
43
  },
 
 
 
 
 
 
44
  "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
+ "mask_token": "[MASK]",
49
+ "max_len": 512,
50
  "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
  }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff