CindyXWu commited on
Commit
1b9ecd1
1 Parent(s): e9c8dbe

Upload tokenizer

Browse files
special_tokens_map.json CHANGED
@@ -1,9 +1,4 @@
1
  {
2
- "additional_special_tokens": [
3
- "<unk>",
4
- "<s>",
5
- "</s>"
6
- ],
7
  "bos_token": {
8
  "content": "<s>",
9
  "lstrip": false,
@@ -11,7 +6,6 @@
11
  "rstrip": false,
12
  "single_word": false
13
  },
14
- "cls_token": "</s>",
15
  "eos_token": {
16
  "content": "</s>",
17
  "lstrip": false,
@@ -19,9 +13,6 @@
19
  "rstrip": false,
20
  "single_word": false
21
  },
22
- "mask_token": "</s>",
23
- "pad_token": "</s>",
24
- "sep_token": "</s>",
25
  "unk_token": {
26
  "content": "<unk>",
27
  "lstrip": false,
 
1
  {
 
 
 
 
 
2
  "bos_token": {
3
  "content": "<s>",
4
  "lstrip": false,
 
6
  "rstrip": false,
7
  "single_word": false
8
  },
 
9
  "eos_token": {
10
  "content": "</s>",
11
  "lstrip": false,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
 
 
 
16
  "unk_token": {
17
  "content": "<unk>",
18
  "lstrip": false,
tokenizer.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
- size 493443
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json CHANGED
@@ -27,25 +27,17 @@
27
  "special": true
28
  }
29
  },
30
- "additional_special_tokens": [
31
- "<unk>",
32
- "<s>",
33
- "</s>"
34
- ],
35
  "bos_token": "<s>",
36
- "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
37
  "clean_up_tokenization_spaces": false,
38
- "cls_token": "</s>",
39
  "eos_token": "</s>",
40
- "legacy": true,
41
- "mask_token": "</s>",
42
  "model_max_length": 1000000000000000019884624838656,
43
- "pad_token": "</s>",
44
- "sep_token": "</s>",
45
  "sp_model_kwargs": {},
46
  "spaces_between_special_tokens": false,
47
  "tokenizer_class": "LlamaTokenizer",
48
- "truncation_side": "left",
49
  "unk_token": "<unk>",
50
- "use_default_system_prompt": true
51
  }
 
27
  "special": true
28
  }
29
  },
 
 
 
 
 
30
  "bos_token": "<s>",
31
+ "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
32
  "clean_up_tokenization_spaces": false,
 
33
  "eos_token": "</s>",
34
+ "legacy": false,
 
35
  "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": null,
37
+ "padding_side": "right",
38
  "sp_model_kwargs": {},
39
  "spaces_between_special_tokens": false,
40
  "tokenizer_class": "LlamaTokenizer",
 
41
  "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
  }