Hugging Face's logo

pjpjpj
/
race-codet5-gpt2

Transformers
PyTorch
t5
text-generation-inference
Inference Endpoints
Model card Files Community
pjpjpj commited on
Commit
e754063
•
1 Parent(s): 6d00737

Upload tokenizer

Browse files
Files changed (6) hide show
  1. added_tokens.json +14 -0
  2. merges.txt +0 -0
  3. special_tokens_map.json +65 -0
  4. tokenizer.json +0 -0
  5. tokenizer_config.json +64 -0
  6. vocab.json +0 -0
added_tokens.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<DELETE>": 32108,
3
+ "<DELETE_END>": 32109,
4
+ "<INSERT>": 32104,
5
+ "<INSERT_END>": 32107,
6
+ "<INSERT_NEW>": 32106,
7
+ "<INSERT_OLD>": 32105,
8
+ "<KEEP>": 32110,
9
+ "<KEEP_END>": 32111,
10
+ "<REPLACE>": 32100,
11
+ "<REPLACE_END>": 32103,
12
+ "<REPLACE_NEW>": 32102,
13
+ "<REPLACE_OLD>": 32101
14
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<REPLACE>",
4
+ "<REPLACE_OLD>",
5
+ "<REPLACE_NEW>",
6
+ "<REPLACE_END>",
7
+ "<INSERT>",
8
+ "<INSERT_OLD>",
9
+ "<INSERT_NEW>",
10
+ "<INSERT_END>",
11
+ "<DELETE>",
12
+ "<DELETE_END>",
13
+ "<KEEP>",
14
+ "<KEEP_END>"
15
+ ],
16
+ "bos_token": {
17
+ "content": "<s>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "cls_token": {
24
+ "content": "<s>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "eos_token": {
31
+ "content": "</s>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "mask_token": {
38
+ "content": "<mask>",
39
+ "lstrip": true,
40
+ "normalized": true,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "pad_token": {
45
+ "content": "<pad>",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ },
51
+ "sep_token": {
52
+ "content": "</s>",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false
57
+ },
58
+ "unk_token": {
59
+ "content": "<unk>",
60
+ "lstrip": false,
61
+ "normalized": true,
62
+ "rstrip": false,
63
+ "single_word": false
64
+ }
65
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "cls_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "__type": "AddedToken",
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "errors": "replace",
28
+ "mask_token": {
29
+ "__type": "AddedToken",
30
+ "content": "<mask>",
31
+ "lstrip": true,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false
35
+ },
36
+ "model_max_length": 512,
37
+ "pad_token": {
38
+ "__type": "AddedToken",
39
+ "content": "<pad>",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ "sep_token": {
46
+ "__type": "AddedToken",
47
+ "content": "</s>",
48
+ "lstrip": false,
49
+ "normalized": true,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ },
53
+ "special_tokens_map_file": "/home/peiyi/.cache/huggingface/hub/models--Salesforce--codet5-base/snapshots/4078456db09ba972a3532827a0b5df4da172323c/special_tokens_map.json",
54
+ "tokenizer_class": "RobertaTokenizer",
55
+ "trim_offsets": true,
56
+ "unk_token": {
57
+ "__type": "AddedToken",
58
+ "content": "<unk>",
59
+ "lstrip": false,
60
+ "normalized": true,
61
+ "rstrip": false,
62
+ "single_word": false
63
+ }
64
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff