Hugging Face's logo

brunosan
/
GPT2-impactscience

Text Generation
Transformers
PyTorch
English
gpt2
climate
text-generation-inference
Inference Endpoints
Model card Files Community
1
brunosan commited on
Commit
a8ae124
·
1 Parent(s): 915d446

Upload tokenizer

Browse files
Files changed (4) hide show
  1. merges.txt +0 -0
  2. special_tokens_map.json +21 -18
  3. tokenizer_config.json +31 -24
  4. vocab.json +0 -0
merges.txt CHANGED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,20 +1,23 @@
1
  {
2
- "additional_special_tokens": [
3
- "<special0>",
4
- "<special1>",
5
- "<special2>",
6
- "<special3>",
7
- "<special4>",
8
- "<special5>",
9
- "<special6>",
10
- "<special7>",
11
- "<special8>",
12
- "<special9>"
13
- ],
14
- "bos_token": "<s>",
15
- "cls_token": "</s>",
16
- "mask_token": "<special1>",
17
- "pad_token": "<s>",
18
- "sep_token": "</s>",
19
- "unk_token": "<unk>"
 
 
 
20
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
  }
tokenizer_config.json CHANGED
@@ -1,27 +1,34 @@
1
  {
2
- "additional_special_tokens": [
3
- "<special0>",
4
- "<special1>",
5
- "<special2>",
6
- "<special3>",
7
- "<special4>",
8
- "<special5>",
9
- "<special6>",
10
- "<special7>",
11
- "<special8>",
12
- "<special9>"
13
- ],
14
- "bos_token": "<s>",
15
- "cls_token": "</s>",
16
- "do_lowercase_and_remove_accent": true,
17
- "id2lang": null,
18
- "lang2id": null,
19
- "mask_token": "<special1>",
20
- "model_max_length": 512,
21
- "name_or_path": "xlm-mlm-en-2048",
22
- "pad_token": "<pad>",
23
- "sep_token": "</s>",
24
  "special_tokens_map_file": null,
25
- "tokenizer_class": "XLMTokenizer",
26
- "unk_token": "<unk>"
 
 
 
 
 
 
 
27
  }
 
1
  {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "model_max_length": 1024,
22
+ "name_or_path": "gpt2",
23
+ "pad_token": null,
24
  "special_tokens_map_file": null,
25
+ "tokenizer_class": "GPT2Tokenizer",
26
+ "unk_token": {
27
+ "__type": "AddedToken",
28
+ "content": "<|endoftext|>",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
  }
vocab.json CHANGED
The diff for this file is too large to render. See raw diff