RaduGabriel commited on
Commit
8e4f83c
·
verified ·
1 Parent(s): 361c07f

Upload folder using huggingface_hub

Browse files
Files changed (5) hide show
  1. config.json +4 -3
  2. model.safetensors +2 -2
  3. tokenizer.json +0 -0
  4. tokenizer_config.json +6 -6
  5. vocab.txt +0 -0
config.json CHANGED
@@ -1,9 +1,10 @@
1
  {
2
  "architectures": [
3
- "BertCRFForTokenClassification"
4
  ],
5
  "attention_probs_dropout_prob": 0.1,
6
  "classifier_dropout": null,
 
7
  "hidden_act": "gelu",
8
  "hidden_dropout_prob": 0.1,
9
  "hidden_size": 768,
@@ -27,9 +28,9 @@
27
  "pad_token_id": 0,
28
  "position_embedding_type": "absolute",
29
  "torch_dtype": "float32",
30
- "transformers_version": "4.51.3",
31
  "type_vocab_size": 2,
32
  "use_cache": true,
33
  "use_crf": false,
34
- "vocab_size": 30522
35
  }
 
1
  {
2
  "architectures": [
3
+ "BertForTokenClassification"
4
  ],
5
  "attention_probs_dropout_prob": 0.1,
6
  "classifier_dropout": null,
7
+ "gradient_checkpointing": false,
8
  "hidden_act": "gelu",
9
  "hidden_dropout_prob": 0.1,
10
  "hidden_size": 768,
 
28
  "pad_token_id": 0,
29
  "position_embedding_type": "absolute",
30
  "torch_dtype": "float32",
31
+ "transformers_version": "4.52.3",
32
  "type_vocab_size": 2,
33
  "use_cache": true,
34
  "use_crf": false,
35
+ "vocab_size": 28996
36
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32204b8b85f786826870e57424dc2c333f26fabfc91631c45aff7f70c0bae4d6
3
- size 437961724
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:741e878f83e514f39f3577583020fd45630ac73414fc99b182572b1790d7e7c5
3
+ size 430911284
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -8,7 +8,7 @@
8
  "single_word": false,
9
  "special": true
10
  },
11
- "1": {
12
  "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
@@ -16,7 +16,7 @@
16
  "single_word": false,
17
  "special": true
18
  },
19
- "2": {
20
  "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
@@ -24,7 +24,7 @@
24
  "single_word": false,
25
  "special": true
26
  },
27
- "3": {
28
  "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
@@ -32,7 +32,7 @@
32
  "single_word": false,
33
  "special": true
34
  },
35
- "4": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
@@ -44,10 +44,10 @@
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
  "do_basic_tokenize": true,
47
- "do_lower_case": true,
48
  "extra_special_tokens": {},
49
  "mask_token": "[MASK]",
50
- "model_max_length": 1000000000000000019884624838656,
51
  "never_split": null,
52
  "pad_token": "[PAD]",
53
  "sep_token": "[SEP]",
 
8
  "single_word": false,
9
  "special": true
10
  },
11
+ "100": {
12
  "content": "[UNK]",
13
  "lstrip": false,
14
  "normalized": false,
 
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "101": {
20
  "content": "[CLS]",
21
  "lstrip": false,
22
  "normalized": false,
 
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "102": {
28
  "content": "[SEP]",
29
  "lstrip": false,
30
  "normalized": false,
 
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "103": {
36
  "content": "[MASK]",
37
  "lstrip": false,
38
  "normalized": false,
 
44
  "clean_up_tokenization_spaces": true,
45
  "cls_token": "[CLS]",
46
  "do_basic_tokenize": true,
47
+ "do_lower_case": false,
48
  "extra_special_tokens": {},
49
  "mask_token": "[MASK]",
50
+ "model_max_length": 512,
51
  "never_split": null,
52
  "pad_token": "[PAD]",
53
  "sep_token": "[SEP]",
vocab.txt CHANGED
The diff for this file is too large to render. See raw diff