Hugging Face's logo

Biophin
/
mi-modelo-qa

Safetensors
distilbert
Model card Files
xet
Community
Biophin commited on
Commit
aad810b
·
verified ·
1 Parent(s): 5b5ea4e

Reemplazo con modelo DistilBERT más ágil

Browse files
Files changed (6) hide show
  1. config.json +24 -11
  2. model.safetensors +2 -2
  3. special_tokens_map.json +5 -49
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +23 -27
  6. vocab.txt +0 -0
config.json CHANGED
@@ -1,12 +1,25 @@
1
  {
2
- "model_type": "roberta",
3
- "pipeline_tag": "question-answering",
4
- "architectures": [
5
- "RobertaForQuestionAnswering"
6
- ],
7
- "hidden_size": 768,
8
- "num_attention_heads": 12,
9
- "num_hidden_layers": 12,
10
- "max_position_embeddings": 512,
11
- "vocab_size": 50265
12
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
2
+ "_name_or_path": "distilbert-base-cased-distilled-squad",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForQuestionAnswering"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "hidden_dim": 3072,
11
+ "initializer_range": 0.02,
12
+ "max_position_embeddings": 512,
13
+ "model_type": "distilbert",
14
+ "n_heads": 12,
15
+ "n_layers": 6,
16
+ "output_past": true,
17
+ "pad_token_id": 0,
18
+ "qa_dropout": 0.1,
19
+ "seq_classif_dropout": 0.2,
20
+ "sinusoidal_pos_embds": true,
21
+ "tie_weights_": true,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.47.1",
24
+ "vocab_size": 28996
25
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea7c01c6ac8f7891ad23102e1569c5b414e8d74cbf8d8a587c3c90510c9cc166
3
- size 496250232
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a22511778fce35d5e360770ef55c98c73bbf06cd464fdce907c9026173fe559
3
+ size 260782152
special_tokens_map.json CHANGED
@@ -1,51 +1,7 @@
1
  {
2
- "bos_token": {
3
- "content": "<s>",
4
- "lstrip": false,
5
- "normalized": true,
6
- "rstrip": false,
7
- "single_word": false
8
- },
9
- "cls_token": {
10
- "content": "<s>",
11
- "lstrip": false,
12
- "normalized": true,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "eos_token": {
17
- "content": "</s>",
18
- "lstrip": false,
19
- "normalized": true,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
- "mask_token": {
24
- "content": "<mask>",
25
- "lstrip": true,
26
- "normalized": true,
27
- "rstrip": false,
28
- "single_word": false
29
- },
30
- "pad_token": {
31
- "content": "<pad>",
32
- "lstrip": false,
33
- "normalized": true,
34
- "rstrip": false,
35
- "single_word": false
36
- },
37
- "sep_token": {
38
- "content": "</s>",
39
- "lstrip": false,
40
- "normalized": true,
41
- "rstrip": false,
42
- "single_word": false
43
- },
44
- "unk_token": {
45
- "content": "<unk>",
46
- "lstrip": false,
47
- "normalized": true,
48
- "rstrip": false,
49
- "single_word": false
50
- }
51
  }
 
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
@@ -1,60 +1,56 @@
1
  {
2
- "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
  "0": {
5
- "content": "<s>",
6
  "lstrip": false,
7
- "normalized": true,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  },
12
- "1": {
13
- "content": "<pad>",
14
  "lstrip": false,
15
- "normalized": true,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
19
  },
20
- "2": {
21
- "content": "</s>",
22
  "lstrip": false,
23
- "normalized": true,
24
  "rstrip": false,
25
  "single_word": false,
26
  "special": true
27
  },
28
- "3": {
29
- "content": "<unk>",
30
  "lstrip": false,
31
- "normalized": true,
32
  "rstrip": false,
33
  "single_word": false,
34
  "special": true
35
  },
36
- "50264": {
37
- "content": "<mask>",
38
- "lstrip": true,
39
- "normalized": true,
40
  "rstrip": false,
41
  "single_word": false,
42
  "special": true
43
  }
44
  },
45
- "bos_token": "<s>",
46
  "clean_up_tokenization_spaces": false,
47
- "cls_token": "<s>",
48
  "do_lower_case": false,
49
- "eos_token": "</s>",
50
- "errors": "replace",
51
  "extra_special_tokens": {},
52
- "full_tokenizer_file": null,
53
- "mask_token": "<mask>",
54
  "model_max_length": 512,
55
- "pad_token": "<pad>",
56
- "sep_token": "</s>",
57
- "tokenizer_class": "RobertaTokenizer",
58
- "trim_offsets": true,
59
- "unk_token": "<unk>"
 
60
  }
 
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
+ "100": {
12
+ "content": "[UNK]",
13
  "lstrip": false,
14
+ "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
+ "101": {
20
+ "content": "[CLS]",
21
  "lstrip": false,
22
+ "normalized": false,
23
  "rstrip": false,
24
  "single_word": false,
25
  "special": true
26
  },
27
+ "102": {
28
+ "content": "[SEP]",
29
  "lstrip": false,
30
+ "normalized": false,
31
  "rstrip": false,
32
  "single_word": false,
33
  "special": true
34
  },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
42
  }
43
  },
 
44
  "clean_up_tokenization_spaces": false,
45
+ "cls_token": "[CLS]",
46
  "do_lower_case": false,
 
 
47
  "extra_special_tokens": {},
48
+ "mask_token": "[MASK]",
 
49
  "model_max_length": 512,
50
+ "pad_token": "[PAD]",
51
+ "sep_token": "[SEP]",
52
+ "strip_accents": null,
53
+ "tokenize_chinese_chars": true,
54
+ "tokenizer_class": "DistilBertTokenizer",
55
+ "unk_token": "[UNK]"
56
  }
vocab.txt ADDED
The diff for this file is too large to render. See raw diff