Hugging Face's logo

moonshotai
/
Kimi-K2-Thinking

Text Generation
Transformers
Safetensors
kimi_k2
conversational
custom_code
Eval Results
compressed-tensors
Model card Files
xet
 Community
60

Add converted tokenizer (no trust_remote_code needed)

#55
by ArthurZ HF Staff - opened
base: refs/heads/main
←
from: refs/pr/55
Discussion Files changed
+14
-173
Files changed (3) hide show
  1. .gitattributes +1 -0
  2. tokenizer.json +3 -0
  3. tokenizer_config.json +10 -173
.gitattributes CHANGED
@@ -39,3 +39,4 @@ figures/banner.png filter=lfs diff=lfs merge=lfs -text
39
  figures/kimi-logo.png filter=lfs diff=lfs merge=lfs -text
40
  figures/* filter=lfs diff=lfs merge=lfs -text
41
  *.png filter=lfs diff=lfs merge=lfs -text
 
 
39
  figures/kimi-logo.png filter=lfs diff=lfs merge=lfs -text
40
  figures/* filter=lfs diff=lfs merge=lfs -text
41
  *.png filter=lfs diff=lfs merge=lfs -text
42
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92bd34973326930c17815fed3f1bbb32f2e2a40b621678ed8859a04a59257444
3
+ size 19544742
tokenizer_config.json CHANGED
@@ -1,180 +1,17 @@
1
  {
2
- "added_tokens_decoder": {
3
- "163584": {
4
- "content": "[BOS]",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "163585": {
12
- "content": "[EOS]",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "163586": {
20
- "content": "<|im_end|>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "163587": {
28
- "content": "<|im_user|>",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "163588": {
36
- "content": "<|im_assistant|>",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- },
43
- "163590": {
44
- "content": "<|start_header_id|>",
45
- "lstrip": false,
46
- "normalized": false,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": true
50
- },
51
- "163591": {
52
- "content": "<|end_header_id|>",
53
- "lstrip": false,
54
- "normalized": false,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": true
58
- },
59
- "163593": {
60
- "content": "[EOT]",
61
- "lstrip": false,
62
- "normalized": false,
63
- "rstrip": false,
64
- "single_word": false,
65
- "special": true
66
- },
67
- "163594": {
68
- "content": "<|im_system|>",
69
- "lstrip": false,
70
- "normalized": false,
71
- "rstrip": false,
72
- "single_word": false,
73
- "special": true
74
- },
75
- "163595": {
76
- "content": "<|tool_calls_section_begin|>",
77
- "lstrip": false,
78
- "normalized": false,
79
- "rstrip": false,
80
- "single_word": false,
81
- "special": false
82
- },
83
- "163596": {
84
- "content": "<|tool_calls_section_end|>",
85
- "lstrip": false,
86
- "normalized": false,
87
- "rstrip": false,
88
- "single_word": false,
89
- "special": false
90
- },
91
- "163597": {
92
- "content": "<|tool_call_begin|>",
93
- "lstrip": false,
94
- "normalized": false,
95
- "rstrip": false,
96
- "single_word": false,
97
- "special": false
98
- },
99
- "163598": {
100
- "content": "<|tool_call_argument_begin|>",
101
- "lstrip": false,
102
- "normalized": false,
103
- "rstrip": false,
104
- "single_word": false,
105
- "special": false
106
- },
107
- "163599": {
108
- "content": "<|tool_call_end|>",
109
- "lstrip": false,
110
- "normalized": false,
111
- "rstrip": false,
112
- "single_word": false,
113
- "special": false
114
- },
115
- "163601": {
116
- "content": "<|im_middle|>",
117
- "lstrip": false,
118
- "normalized": false,
119
- "rstrip": false,
120
- "single_word": false,
121
- "special": true
122
- },
123
- "163606": {
124
- "content": "<think>",
125
- "lstrip": false,
126
- "normalized": false,
127
- "rstrip": false,
128
- "single_word": false,
129
- "special": false
130
- },
131
- "163607": {
132
- "content": "</think>",
133
- "lstrip": false,
134
- "normalized": false,
135
- "rstrip": false,
136
- "single_word": false,
137
- "special": false
138
- },
139
- "163838": {
140
- "content": "[UNK]",
141
- "lstrip": false,
142
- "normalized": false,
143
- "rstrip": false,
144
- "single_word": false,
145
- "special": true
146
- },
147
- "163839": {
148
- "content": "[PAD]",
149
- "lstrip": false,
150
- "normalized": false,
151
- "rstrip": false,
152
- "single_word": false,
153
- "special": true
154
- }
155
  },
156
- "additional_special_tokens": [
157
- "<|im_end|>",
158
- "<|im_user|>",
159
- "<|im_assistant|>",
160
- "<|start_header_id|>",
161
- "<|end_header_id|>",
162
- "[EOT]",
163
- "<|im_system|>",
164
- "<|im_middle|>"
165
- ],
166
  "bos_token": "[BOS]",
167
  "clean_up_tokenization_spaces": false,
168
  "eos_token": "[EOS]",
169
- "extra_special_tokens": {},
170
  "model_max_length": 1000000000000000019884624838656,
171
  "pad_token": "[PAD]",
172
- "tokenizer_class": "TikTokenTokenizer",
173
- "unk_token": "[UNK]",
174
- "auto_map": {
175
- "AutoTokenizer": [
176
- "tokenization_kimi.TikTokenTokenizer",
177
- null
178
- ]
179
- }
180
- }
 
1
  {
2
+ "auto_map": {
3
+ "AutoTokenizer": [
4
+ "tokenization_kimi.TikTokenTokenizer",
5
+ null
6
+ ]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  },
8
+ "backend": "tokenizers",
 
 
 
 
 
 
 
 
 
9
  "bos_token": "[BOS]",
10
  "clean_up_tokenization_spaces": false,
11
  "eos_token": "[EOS]",
12
+ "is_local": false,
13
  "model_max_length": 1000000000000000019884624838656,
14
  "pad_token": "[PAD]",
15
+ "tokenizer_class": "TokenizersBackend",
16
+ "unk_token": "[UNK]"
17
+ }