Hugging Face's logo

mmenendezg
/
xlm-roberta-base-pharmaconer

Token Classification
Transformers
PyTorch
xlm-roberta
Generated from Trainer
Inference Endpoints
Model card Files Community
mmenendezg commited on
Commit
b7d00cc
•
1 Parent(s): f8a5f81

Training in progress, step 1000

Browse files
Files changed (7) hide show
  1. merges.txt +0 -0
  2. pytorch_model.bin +1 -1
  3. special_tokens_map.json +43 -7
  4. tokenizer.json +2 -2
  5. tokenizer_config.json +53 -7
  6. training_args.bin +1 -1
  7. vocab.json +0 -0
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7179ab673fc8a0bad7248c1b01c000bce9ec28de53a6809a09e484ef57129765
3
  size 1109905449
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b24767aad457449b5096e72b87799751c9c5cbdb9f4434bafed1d95f38250a6
3
  size 1109905449
special_tokens_map.json CHANGED
@@ -1,15 +1,51 @@
1
  {
2
- "bos_token": "<s>",
3
- "cls_token": "<s>",
4
- "eos_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "mask_token": {
6
  "content": "<mask>",
7
  "lstrip": true,
8
- "normalized": false,
9
  "rstrip": false,
10
  "single_word": false
11
  },
12
- "pad_token": "<pad>",
13
- "sep_token": "</s>",
14
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
15
  }
 
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
  }
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
3
- size 17082758
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2758813d862050b0afcafa566f4ded61e06efef526142104b65810463a77d19
3
+ size 2321571
tokenizer_config.json CHANGED
@@ -1,8 +1,31 @@
1
  {
2
- "bos_token": "<s>",
 
 
 
 
 
 
 
 
3
  "clean_up_tokenization_spaces": true,
4
- "cls_token": "<s>",
5
- "eos_token": "</s>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  "mask_token": {
7
  "__type": "AddedToken",
8
  "content": "<mask>",
@@ -11,9 +34,32 @@
11
  "rstrip": false,
12
  "single_word": false
13
  },
 
14
  "model_max_length": 512,
15
- "pad_token": "<pad>",
16
- "sep_token": "</s>",
17
- "tokenizer_class": "XLMRobertaTokenizer",
18
- "unk_token": "<unk>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
19
  }
 
1
  {
2
+ "add_prefix_space": true,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
  "clean_up_tokenization_spaces": true,
12
+ "cls_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "eos_token": {
21
+ "__type": "AddedToken",
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "errors": "replace",
29
  "mask_token": {
30
  "__type": "AddedToken",
31
  "content": "<mask>",
 
34
  "rstrip": false,
35
  "single_word": false
36
  },
37
+ "max_len": 512,
38
  "model_max_length": 512,
39
+ "pad_token": {
40
+ "__type": "AddedToken",
41
+ "content": "<pad>",
42
+ "lstrip": false,
43
+ "normalized": true,
44
+ "rstrip": false,
45
+ "single_word": false
46
+ },
47
+ "sep_token": {
48
+ "__type": "AddedToken",
49
+ "content": "</s>",
50
+ "lstrip": false,
51
+ "normalized": true,
52
+ "rstrip": false,
53
+ "single_word": false
54
+ },
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": {
58
+ "__type": "AddedToken",
59
+ "content": "<unk>",
60
+ "lstrip": false,
61
+ "normalized": true,
62
+ "rstrip": false,
63
+ "single_word": false
64
+ }
65
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa957fa0ef160873f4061755f2473f0ccb08e623174c11b08b48191d986c72cc
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a65c36a0ad131ad95581352f693c800aea496b3000120bc11592efd3c543449
3
  size 4091
vocab.json ADDED
The diff for this file is too large to render. See raw diff