deepnet commited on
Commit
667a62f
·
verified ·
1 Parent(s): 20da301

Upload tokenizer

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +0 -7
  2. tokenizer.json +6 -19
  3. tokenizer_config.json +8 -23
special_tokens_map.json CHANGED
@@ -7,13 +7,6 @@
7
  "single_word": false
8
  },
9
  "eos_token": {
10
- "content": "<|im_end|>",
11
- "lstrip": false,
12
- "normalized": false,
13
- "rstrip": false,
14
- "single_word": false
15
- },
16
- "pad_token": {
17
  "content": "</s>",
18
  "lstrip": false,
19
  "normalized": false,
 
7
  "single_word": false
8
  },
9
  "eos_token": {
 
 
 
 
 
 
 
10
  "content": "</s>",
11
  "lstrip": false,
12
  "normalized": false,
tokenizer.json CHANGED
@@ -1,6 +1,11 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
@@ -29,24 +34,6 @@
29
  "rstrip": false,
30
  "normalized": false,
31
  "special": true
32
- },
33
- {
34
- "id": 32000,
35
- "content": "<|im_end|>",
36
- "single_word": false,
37
- "lstrip": false,
38
- "rstrip": false,
39
- "normalized": false,
40
- "special": true
41
- },
42
- {
43
- "id": 32001,
44
- "content": "<|im_start|>",
45
- "single_word": false,
46
- "lstrip": false,
47
- "rstrip": false,
48
- "normalized": false,
49
- "special": true
50
  }
51
  ],
52
  "normalizer": {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 2048,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
34
  "rstrip": false,
35
  "normalized": false,
36
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
37
  }
38
  ],
39
  "normalizer": {
tokenizer_config.json CHANGED
@@ -25,37 +25,22 @@
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
28
- },
29
- "32000": {
30
- "content": "<|im_end|>",
31
- "lstrip": false,
32
- "normalized": false,
33
- "rstrip": false,
34
- "single_word": false,
35
- "special": true
36
- },
37
- "32001": {
38
- "content": "<|im_start|>",
39
- "lstrip": false,
40
- "normalized": false,
41
- "rstrip": false,
42
- "single_word": false,
43
- "special": true
44
  }
45
  },
46
  "additional_special_tokens": [],
47
  "bos_token": "<s>",
48
- "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 %}",
49
  "clean_up_tokenization_spaces": false,
50
- "eos_token": "<|im_end|>",
51
  "legacy": true,
52
- "model_max_length": 2048,
53
- "pad_token": "</s>",
 
54
  "sp_model_kwargs": {},
55
  "spaces_between_special_tokens": false,
 
56
  "tokenizer_class": "LlamaTokenizer",
57
- "trust_remote_code": false,
 
58
  "unk_token": "<unk>",
59
- "use_default_system_prompt": true,
60
- "use_fast": true
61
  }
 
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
  }
29
  },
30
  "additional_special_tokens": [],
31
  "bos_token": "<s>",
 
32
  "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
  "legacy": true,
35
+ "max_length": 2048,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": null,
38
  "sp_model_kwargs": {},
39
  "spaces_between_special_tokens": false,
40
+ "stride": 0,
41
  "tokenizer_class": "LlamaTokenizer",
42
+ "truncation_side": "right",
43
+ "truncation_strategy": "longest_first",
44
  "unk_token": "<unk>",
45
+ "use_default_system_prompt": false
 
46
  }