Hugging Face's logo

Sirawipa
/
tian-ft

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
Sirawipa commited on
Commit
7220b01
·
verified ·
1 Parent(s): e0ba7ea

Upload tokenizer

Browse files
Files changed (7) hide show
  1. README.md +1 -1
  2. added_tokens.json +5 -0
  3. merges.txt +0 -0
  4. special_tokens_map.json +4 -37
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +19 -88
  7. vocab.json +0 -0
README.md CHANGED
@@ -1,8 +1,8 @@
1
  ---
2
  license: apache-2.0
3
- base_model: sail/Sailor-0.5B
4
  tags:
5
  - generated_from_trainer
 
6
  model-index:
7
  - name: tian-ft
8
  results: []
 
1
  ---
2
  license: apache-2.0
 
3
  tags:
4
  - generated_from_trainer
5
+ base_model: sail/Sailor-0.5B
6
  model-index:
7
  - name: tian-ft
8
  results: []
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json CHANGED
@@ -1,47 +1,14 @@
1
  {
2
  "additional_special_tokens": [
3
- "<madeupword0>",
4
- "<madeupword1>",
5
- "<madeupword2>",
6
- "<madeupword3>",
7
- "<madeupword4>",
8
- "<madeupword5>",
9
- "<madeupword6>"
10
  ],
11
- "bos_token": {
12
- "content": "<s>",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false
17
- },
18
- "cls_token": {
19
- "content": "<s>",
20
- "lstrip": false,
21
- "normalized": false,
22
- "rstrip": false,
23
- "single_word": false
24
- },
25
  "eos_token": {
26
- "content": "</s>",
27
  "lstrip": false,
28
  "normalized": false,
29
  "rstrip": false,
30
  "single_word": false
31
  },
32
- "pad_token": "</s>",
33
- "sep_token": {
34
- "content": "</s>",
35
- "lstrip": false,
36
- "normalized": false,
37
- "rstrip": false,
38
- "single_word": false
39
- },
40
- "unk_token": {
41
- "content": "<unk>",
42
- "lstrip": false,
43
- "normalized": false,
44
- "rstrip": false,
45
- "single_word": false
46
- }
47
  }
 
1
  {
2
  "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
 
 
 
 
 
5
  ],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  "eos_token": {
7
+ "content": "<|endoftext|>",
8
  "lstrip": false,
9
  "normalized": false,
10
  "rstrip": false,
11
  "single_word": false
12
  },
13
+ "pad_token": "<|endoftext|>"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,87 +1,24 @@
1
  {
 
2
  "added_tokens_decoder": {
3
- "0": {
4
- "content": "<s>",
5
  "lstrip": false,
6
  "normalized": false,
7
  "rstrip": false,
8
  "single_word": false,
9
  "special": true
10
  },
11
- "1": {
12
- "content": "<pad>",
13
  "lstrip": false,
14
  "normalized": false,
15
  "rstrip": false,
16
  "single_word": false,
17
  "special": true
18
  },
19
- "2": {
20
- "content": "</s>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "3": {
28
- "content": "<unk>",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "256001": {
36
- "content": "<madeupword0>",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- },
43
- "256002": {
44
- "content": "<madeupword1>",
45
- "lstrip": false,
46
- "normalized": false,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": true
50
- },
51
- "256003": {
52
- "content": "<madeupword2>",
53
- "lstrip": false,
54
- "normalized": false,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": true
58
- },
59
- "256004": {
60
- "content": "<madeupword3>",
61
- "lstrip": false,
62
- "normalized": false,
63
- "rstrip": false,
64
- "single_word": false,
65
- "special": true
66
- },
67
- "256005": {
68
- "content": "<madeupword4>",
69
- "lstrip": false,
70
- "normalized": false,
71
- "rstrip": false,
72
- "single_word": false,
73
- "special": true
74
- },
75
- "256006": {
76
- "content": "<madeupword5>",
77
- "lstrip": false,
78
- "normalized": false,
79
- "rstrip": false,
80
- "single_word": false,
81
- "special": true
82
- },
83
- "256007": {
84
- "content": "<madeupword6>",
85
  "lstrip": false,
86
  "normalized": false,
87
  "rstrip": false,
@@ -90,23 +27,17 @@
90
  }
91
  },
92
  "additional_special_tokens": [
93
- "<madeupword0>",
94
- "<madeupword1>",
95
- "<madeupword2>",
96
- "<madeupword3>",
97
- "<madeupword4>",
98
- "<madeupword5>",
99
- "<madeupword6>"
100
  ],
101
- "bos_token": "<s>",
102
- "clean_up_tokenization_spaces": true,
103
- "cls_token": "<s>",
104
- "eos_token": "</s>",
105
- "model_max_length": 1000000000000000019884624838656,
106
- "pad_token": "</s>",
107
- "sep_token": "</s>",
108
- "sp_model_kwargs": {},
109
- "tokenizer_class": "XGLMTokenizer",
110
- "unk_token": "<unk>",
111
- "use_fast": true
112
  }
 
1
  {
2
+ "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
  "lstrip": false,
7
  "normalized": false,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
11
  },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
  "lstrip": false,
15
  "normalized": false,
16
  "rstrip": false,
17
  "single_word": false,
18
  "special": true
19
  },
20
+ "151645": {
21
+ "content": "<|im_end|>",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22
  "lstrip": false,
23
  "normalized": false,
24
  "rstrip": false,
 
27
  }
28
  },
29
  "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
 
 
 
 
 
32
  ],
33
+ "bos_token": null,
34
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|endoftext|>",
37
+ "errors": "replace",
38
+ "model_max_length": 32768,
39
+ "pad_token": "<|endoftext|>",
40
+ "split_special_tokens": false,
41
+ "tokenizer_class": "Qwen2Tokenizer",
42
+ "unk_token": null
 
43
  }
vocab.json ADDED
The diff for this file is too large to render. See raw diff