Hugging Face's logo

michaelbenayoun
/
deepseekv3-tiny-4kv-heads-4-layers-random

Text Generation
Transformers
Safetensors
deepseek_v3
custom_code
text-generation-inference
fp8
Model card Files
xet
Community
michaelbenayoun HF Staff commited on
Commit
87ffd32
·
verified ·
1 Parent(s): e17a807

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +40 -0
  2. tiktoken.model +3 -0
  3. tokenizer_config.json +125 -0
special_tokens_map.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_end|>",
4
+ "<|im_user|>",
5
+ "<|im_assistant|>",
6
+ "<|start_header_id|>",
7
+ "<|end_header_id|>",
8
+ "[EOT]",
9
+ "<|im_system|>",
10
+ "<|im_middle|>"
11
+ ],
12
+ "bos_token": {
13
+ "content": "[BOS]",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "content": "[EOS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "pad_token": {
27
+ "content": "[PAD]",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "unk_token": {
34
+ "content": "[UNK]",
35
+ "lstrip": false,
36
+ "normalized": false,
37
+ "rstrip": false,
38
+ "single_word": false
39
+ }
40
+ }
tiktoken.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6c497a7469b33ced9c38afb1ad6e47f03f5e5dc05f15930799210ec050c5103
3
+ size 2795286
tokenizer_config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "163601": {
76
+ "content": "<|im_middle|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "163838": {
84
+ "content": "[UNK]",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "163839": {
92
+ "content": "[PAD]",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ }
99
+ },
100
+ "additional_special_tokens": [
101
+ "<|im_end|>",
102
+ "<|im_user|>",
103
+ "<|im_assistant|>",
104
+ "<|start_header_id|>",
105
+ "<|end_header_id|>",
106
+ "[EOT]",
107
+ "<|im_system|>",
108
+ "<|im_middle|>"
109
+ ],
110
+ "auto_map": {
111
+ "AutoTokenizer": [
112
+ "moonshotai/Kimi-K2-Base--tokenization_kimi.TikTokenTokenizer",
113
+ null
114
+ ]
115
+ },
116
+ "bos_token": "[BOS]",
117
+ "chat_template": "{% if tools -%}\n {{ '<|im_system|>tool_declare<|im_middle|>' -}}\n {{- tools | tojson -}}\n {{ '<|im_end|>' -}}\n{%- endif -%}\n\n{%- for message in messages -%}\n {%- if loop.first and messages[0]['role'] != 'system' -%}\n {{ '<|im_system|>system<|im_middle|>You are a helpful assistant<|im_end|>' }}\n {%- endif -%}\n {%- if message['role'] == 'system' -%}\n {{ '<|im_system|>system<|im_middle|>' }}\n {%- elif message['role'] == 'user' -%}\n {{ '<|im_user|>user<|im_middle|>' }}\n {%- elif message['role'] == 'assistant' -%}\n {{ '<|im_assistant|>assistant<|im_middle|>' }}\n {%- elif message['role'] == 'tool' -%}\n {{ '<|im_system|>tool<|im_middle|>' }}\n {%- endif -%}\n\n {%- if message['content'] is string -%}\n {{- message['content'] + '<|im_end|>' -}}\n {%- else -%}\n {%- for content in message['content'] -%}\n {%- if content['type'] == 'image' or 'image' in content or 'image_url' in content -%}\n {{ '<|media_start|>image<|media_content|><|media_pad|><|media_end|>' }}\n {%- else -%}\n {{ content['text'] }}\n {%- endif -%}\n {%- endfor -%}\n {{ '<|im_end|>' }}\n {%- endif -%}\n{%- endfor -%}\n\n{%- if add_generation_prompt -%}\n {{ '<|im_assistant|>assistant<|im_middle|>' }}\n{%- endif -%}",
118
+ "clean_up_tokenization_spaces": false,
119
+ "eos_token": "[EOS]",
120
+ "extra_special_tokens": {},
121
+ "model_max_length": 1000000000000000019884624838656,
122
+ "pad_token": "[PAD]",
123
+ "tokenizer_class": "TikTokenTokenizer",
124
+ "unk_token": "[UNK]"
125
+ }