Hugging Face's logo

Spaces:
devoppro
/
CodeLLM
Runtime error

App Files Community
devoppro commited on
Commit
2407416
·
verified ·
1 Parent(s): a48661e

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. checkpoints/tokenizer/added_tokens.json +11 -0
  2. checkpoints/tokenizer/merges.txt +0 -0
  3. checkpoints/tokenizer/special_tokens_map.json +71 -0
  4. checkpoints/tokenizer/tokenizer.json +0 -0
  5. checkpoints/tokenizer/tokenizer_config.json +103 -0
  6. checkpoints/tokenizer/vocab.json +0 -0
checkpoints/tokenizer/added_tokens.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|cpp|>": 50265,
3
+ "<|fim_middle|>": 50258,
4
+ "<|fim_prefix|>": 50257,
5
+ "<|fim_suffix|>": 50259,
6
+ "<|go|>": 50263,
7
+ "<|javascript|>": 50261,
8
+ "<|python|>": 50260,
9
+ "<|rust|>": 50262,
10
+ "<|typescript|>": 50264
11
+ }
checkpoints/tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|fim_prefix|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|fim_middle|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<|fim_suffix|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "<|python|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<|javascript|>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "<|rust|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "<|go|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "<|typescript|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ },
59
+ {
60
+ "content": "<|cpp|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ }
66
+ ],
67
+ "bos_token": "<|endoftext|>",
68
+ "eos_token": "<|endoftext|>",
69
+ "pad_token": "<|endoftext|>",
70
+ "unk_token": "<|endoftext|>"
71
+ }
checkpoints/tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoints/tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|fim_prefix|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "50258": {
21
+ "content": "<|fim_middle|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "50259": {
29
+ "content": "<|fim_suffix|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "50260": {
37
+ "content": "<|python|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "50261": {
45
+ "content": "<|javascript|>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "50262": {
53
+ "content": "<|rust|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "50263": {
61
+ "content": "<|go|>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "50264": {
69
+ "content": "<|typescript|>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "50265": {
77
+ "content": "<|cpp|>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ }
84
+ },
85
+ "additional_special_tokens": [
86
+ "<|fim_prefix|>",
87
+ "<|fim_middle|>",
88
+ "<|fim_suffix|>",
89
+ "<|python|>",
90
+ "<|javascript|>",
91
+ "<|rust|>",
92
+ "<|go|>",
93
+ "<|typescript|>",
94
+ "<|cpp|>"
95
+ ],
96
+ "bos_token": "<|endoftext|>",
97
+ "clean_up_tokenization_spaces": true,
98
+ "eos_token": "<|endoftext|>",
99
+ "model_max_length": 1024,
100
+ "pad_token": "<|endoftext|>",
101
+ "tokenizer_class": "GPT2Tokenizer",
102
+ "unk_token": "<|endoftext|>"
103
+ }
checkpoints/tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff