Hugging Face's logo

isbondarev
/
MiniCPM4-8B-test-adv

Feature Extraction
Transformers
Safetensors
minicpm
llama-factory
custom_code
Model card Files
xet
Community
isbondarev commited on
Commit
af51fb8
·
verified ·
1 Parent(s): 3bc5a8d

Upload tokenizer

Browse files
Files changed (6) hide show
  1. added_tokens.json +10 -0
  2. chat_template.jinja +4 -0
  3. special_tokens_map.json +34 -0
  4. tokenizer.json +0 -0
  5. tokenizer.model +3 -0
  6. tokenizer_config.json +119 -0
added_tokens.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|execute_end|>": 73444,
3
+ "<|execute_start|>": 73443,
4
+ "<|fim_middle|>": 73446,
5
+ "<|fim_prefix|>": 73445,
6
+ "<|fim_suffix|>": 73447,
7
+ "<|im_end|>": 73440,
8
+ "<|im_start|>": 73441,
9
+ "<|tool_call|>": 73442
10
+ }
chat_template.jinja ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {% for message in messages %}{{'<|im_start|>' + message['role'] + '
2
+ ' + message['content'] + '<|im_end|>' + '
3
+ '}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
4
+ ' }}{% endif %}
special_tokens_map.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_end|>",
4
+ "<|im_start|>",
5
+ "<|tool_call|>",
6
+ "<|execute_start|>",
7
+ "<|execute_end|>",
8
+ "<|fim_prefix|>",
9
+ "<|fim_middle|>",
10
+ "<|fim_suffix|>"
11
+ ],
12
+ "bos_token": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "content": "<|im_end|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ },
26
+ "pad_token": "<|im_end|>",
27
+ "unk_token": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false
33
+ }
34
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb74d51116831c3bf65db812c553f94ab0c88dcf97a5bbb37e3504f6d359c530
3
+ size 1181204
tokenizer_config.json ADDED
@@ -0,0 +1,119 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ },
30
+ "73440": {
31
+ "content": "<|im_end|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "73441": {
39
+ "content": "<|im_start|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "73442": {
47
+ "content": "<|tool_call|>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "73443": {
55
+ "content": "<|execute_start|>",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "73444": {
63
+ "content": "<|execute_end|>",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ },
70
+ "73445": {
71
+ "content": "<|fim_prefix|>",
72
+ "lstrip": false,
73
+ "normalized": false,
74
+ "rstrip": false,
75
+ "single_word": false,
76
+ "special": true
77
+ },
78
+ "73446": {
79
+ "content": "<|fim_middle|>",
80
+ "lstrip": false,
81
+ "normalized": false,
82
+ "rstrip": false,
83
+ "single_word": false,
84
+ "special": true
85
+ },
86
+ "73447": {
87
+ "content": "<|fim_suffix|>",
88
+ "lstrip": false,
89
+ "normalized": false,
90
+ "rstrip": false,
91
+ "single_word": false,
92
+ "special": true
93
+ }
94
+ },
95
+ "additional_special_tokens": [
96
+ "<|im_end|>",
97
+ "<|im_start|>",
98
+ "<|tool_call|>",
99
+ "<|execute_start|>",
100
+ "<|execute_end|>",
101
+ "<|fim_prefix|>",
102
+ "<|fim_middle|>",
103
+ "<|fim_suffix|>"
104
+ ],
105
+ "bos_token": "<s>",
106
+ "clean_up_tokenization_spaces": false,
107
+ "eos_token": "<|im_end|>",
108
+ "extra_special_tokens": {},
109
+ "legacy": true,
110
+ "model_max_length": 1000000000000000019884624838656,
111
+ "pad_token": "<|im_end|>",
112
+ "padding_side": "left",
113
+ "sp_model_kwargs": {},
114
+ "spaces_between_special_tokens": false,
115
+ "split_special_tokens": false,
116
+ "tokenizer_class": "LlamaTokenizer",
117
+ "unk_token": "<unk>",
118
+ "use_default_system_prompt": false
119
+ }