Hugging Face's logo

Xenova
/
internlm2-tokenizer

Model card Files Community
Xenova HF staff commited on
Commit
4ca67aa
•
1 Parent(s): 0401b54

Upload 4 files

Browse files
Files changed (4) hide show
  1. special_tokens_map.json +38 -0
  2. tokenizer.json +0 -0
  3. tokenizer.model +3 -0
  4. tokenizer_config.json +102 -0
special_tokens_map.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|action_start|>",
6
+ "<|action_end|>",
7
+ "<|interpreter|>",
8
+ "<|plugin|>"
9
+ ],
10
+ "bos_token": {
11
+ "content": "<s>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ "eos_token": {
18
+ "content": "</s>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "</s>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "unk_token": {
32
+ "content": "<unk>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ }
38
+ }
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:f868398fc4e05ee1e8aeba95ddf18ddcc45b8bce55d5093bead5bbf80429b48b
3
+ size 1477754
tokenizer_config.json ADDED
@@ -0,0 +1,102 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "92538": {
30
+ "content": "<|plugin|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "92539": {
38
+ "content": "<|interpreter|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "92540": {
46
+ "content": "<|action_end|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "92541": {
54
+ "content": "<|action_start|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "92542": {
62
+ "content": "<|im_end|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "92543": {
70
+ "content": "<|im_start|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ }
77
+ },
78
+ "additional_special_tokens": [
79
+ "<|im_start|>",
80
+ "<|im_end|>",
81
+ "<|action_start|>",
82
+ "<|action_end|>",
83
+ "<|interpreter|>",
84
+ "<|plugin|>"
85
+ ],
86
+ "auto_map": {
87
+ "AutoTokenizer": [
88
+ "tokenization_internlm2.InternLM2Tokenizer",
89
+ "tokenization_internlm2_fast.InternLM2TokenizerFast"
90
+ ]
91
+ },
92
+ "bos_token": "<s>",
93
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
94
+ "clean_up_tokenization_spaces": false,
95
+ "decode_with_prefix_space": false,
96
+ "eos_token": "</s>",
97
+ "model_max_length": 1000000000000000019884624838656,
98
+ "pad_token": "</s>",
99
+ "sp_model_kwargs": null,
100
+ "tokenizer_class": "InternLM2Tokenizer",
101
+ "unk_token": "<unk>"
102
+ }