Hugging Face's logo

burnninghotel
/
architect-model

Text Generation
Transformers
Safetensors
gpt2
text-generation-inference
Model card Files
xet
Community
burnninghotel commited on
Commit
cc14d7e
·
verified ·
1 Parent(s): 2b9da83

Upload tokenizer

Browse files
Files changed (6) hide show
  1. added_tokens.json +5 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +44 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +54 -0
  6. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "[CLS]": 50259,
3
+ "[PAD]": 50257,
4
+ "[SEP]": 50258
5
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "[CLS]",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "[PAD]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "sep_token": {
31
+ "content": "[SEP]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "unk_token": {
38
+ "content": "<|endoftext|>",
39
+ "lstrip": false,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ }
44
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,54 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "50257": {
13
+ "content": "[PAD]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "50258": {
21
+ "content": "[SEP]",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "50259": {
29
+ "content": "[CLS]",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ }
36
+ },
37
+ "bos_token": "<|endoftext|>",
38
+ "clean_up_tokenization_spaces": false,
39
+ "cls_token": "[CLS]",
40
+ "eos_token": "<|endoftext|>",
41
+ "extra_special_tokens": {},
42
+ "max_length": 512,
43
+ "model_max_length": 1024,
44
+ "pad_to_multiple_of": null,
45
+ "pad_token": "[PAD]",
46
+ "pad_token_type_id": 0,
47
+ "padding_side": "right",
48
+ "sep_token": "[SEP]",
49
+ "stride": 0,
50
+ "tokenizer_class": "GPT2Tokenizer",
51
+ "truncation_side": "right",
52
+ "truncation_strategy": "longest_first",
53
+ "unk_token": "<|endoftext|>"
54
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff