Hugging Face's logo

momergul
/
babylm-baseline-100m-gpt2

Text Generation
Transformers
Safetensors
gpt2
text-generation-inference
Model card Files
xet
Community
momergul commited on
Commit
340fe4d
·
verified ·
1 Parent(s): 99e5436

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +28 -3
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +43 -8
special_tokens_map.json CHANGED
@@ -1,5 +1,30 @@
1
  {
2
- "bos_token": "<|endoftext|>",
3
- "eos_token": "<|endoftext|>",
4
- "unk_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  }
 
1
  {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,20 +1,55 @@
1
  {
2
- "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
- "50256": {
5
- "content": "<|endoftext|>",
6
  "lstrip": false,
7
- "normalized": true,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  }
12
  },
13
- "bos_token": "<|endoftext|>",
14
  "clean_up_tokenization_spaces": false,
15
- "eos_token": "<|endoftext|>",
 
16
  "extra_special_tokens": {},
 
17
  "model_max_length": 1024,
18
- "tokenizer_class": "GPT2Tokenizer",
19
- "unk_token": "<|endoftext|>"
 
 
20
  }
 
1
  {
 
2
  "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
  "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<pad>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "4": {
36
+ "content": "<mask>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
  "rstrip": false,
40
  "single_word": false,
41
  "special": true
42
  }
43
  },
44
+ "bos_token": "<s>",
45
  "clean_up_tokenization_spaces": false,
46
+ "cls_token": null,
47
+ "eos_token": "</s>",
48
  "extra_special_tokens": {},
49
+ "mask_token": null,
50
  "model_max_length": 1024,
51
+ "pad_token": "<pad>",
52
+ "sep_token": null,
53
+ "tokenizer_class": "PreTrainedTokenizer",
54
+ "unk_token": "<unk>"
55
  }