hammeiam commited on
Commit
b3b34ce
1 Parent(s): 418354e

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|im_end|>": 32000,
3
+ "<|im_start|>": 32001
4
+ }
special_tokens_map.json CHANGED
@@ -7,7 +7,7 @@
7
  "single_word": false
8
  },
9
  "eos_token": {
10
- "content": "</s>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
 
7
  "single_word": false
8
  },
9
  "eos_token": {
10
+ "content": "<|im_end|>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
tokenizer.json CHANGED
@@ -1,11 +1,6 @@
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
  {
@@ -34,6 +29,24 @@
34
  "rstrip": false,
35
  "normalized": false,
36
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
37
  }
38
  ],
39
  "normalizer": {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
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": {
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json CHANGED
@@ -25,23 +25,37 @@
25
  "rstrip": false,
26
  "single_word": false,
27
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
28
  }
29
  },
30
  "additional_special_tokens": [],
31
  "bos_token": "<s>",
32
- "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token + ' ' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
33
  "clean_up_tokenization_spaces": false,
34
- "eos_token": "</s>",
35
  "legacy": true,
36
- "max_length": 2048,
37
  "model_max_length": 1000000000000000019884624838656,
38
  "pad_token": null,
39
  "sp_model_kwargs": {},
40
  "spaces_between_special_tokens": false,
41
- "stride": 0,
42
  "tokenizer_class": "LlamaTokenizer",
43
- "truncation_side": "right",
44
- "truncation_strategy": "longest_first",
45
  "unk_token": "<unk>",
46
- "use_default_system_prompt": false
 
47
  }
 
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": 1000000000000000019884624838656,
53
  "pad_token": null,
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
  }