khtsly commited on
Commit
fc43f32
·
verified ·
1 Parent(s): ba99d76

Update tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +102 -14
tokenizer_config.json CHANGED
@@ -1,20 +1,108 @@
1
  {
2
- "backend": "tokenizers",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "bos_token": null,
4
  "eos_token": "<|im_end|>",
5
- "extra_special_tokens": [
6
- "<|im_start|>",
7
- "<|im_end|>",
8
- "<think>",
9
- "</think>",
10
- "<|fim_prefix|>",
11
- "<|fim_middle|>",
12
- "<|fim_suffix|>",
13
- "<tool_call>",
14
- "</tool_call>",
15
- "<tool_response>",
16
- "</tool_response>"
17
- ],
18
  "model_max_length": 1000000000000000019884624838656,
19
  "pad_token": "<|endoftext|>",
20
  "tokenizer_class": "PreTrainedTokenizerFast",
 
1
  {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<|endoftext|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<|im_start|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<|im_end|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<think>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "4": {
36
+ "content": "</think>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "5": {
44
+ "content": "<|fim_prefix|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "6": {
52
+ "content": "<|fim_middle|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "7": {
60
+ "content": "<|fim_suffix|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "32764": {
68
+ "content": "<tool_call>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "32765": {
76
+ "content": "</tool_call>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "32766": {
84
+ "content": "<tool_response>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "32767": {
92
+ "content": "</tool_response>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ }
99
+ },
100
+ "additional_special_tokens": [
101
+ "<|im_start|>",
102
+ "<|im_end|>"
103
+ ],
104
  "bos_token": null,
105
  "eos_token": "<|im_end|>",
 
 
 
 
 
 
 
 
 
 
 
 
 
106
  "model_max_length": 1000000000000000019884624838656,
107
  "pad_token": "<|endoftext|>",
108
  "tokenizer_class": "PreTrainedTokenizerFast",