keylazy commited on
Commit
0173b6a
1 Parent(s): 008bf11

Upload tokenizer

Browse files
special_tokens_map.json CHANGED
@@ -1,7 +1,4 @@
1
  {
2
- "additional_special_tokens": [
3
- "pad_token"
4
- ],
5
  "bos_token": {
6
  "content": "<s>",
7
  "lstrip": false,
@@ -16,6 +13,7 @@
16
  "rstrip": false,
17
  "single_word": false
18
  },
 
19
  "unk_token": {
20
  "content": "<unk>",
21
  "lstrip": false,
 
1
  {
 
 
 
2
  "bos_token": {
3
  "content": "<s>",
4
  "lstrip": false,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": "<pad>",
17
  "unk_token": {
18
  "content": "<unk>",
19
  "lstrip": false,
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -25,7 +25,7 @@
25
  "special": true
26
  },
27
  "3": {
28
- "content": "pad_token",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
@@ -33,16 +33,13 @@
33
  "special": true
34
  }
35
  },
36
- "additional_special_tokens": [
37
- "pad_token"
38
- ],
39
  "bos_token": "<s>",
40
  "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 %}",
41
  "clean_up_tokenization_spaces": false,
42
  "eos_token": "</s>",
43
  "legacy": false,
44
  "model_max_length": 1000000000000000019884624838656,
45
- "pad_token": null,
46
  "padding_side": "right",
47
  "sp_model_kwargs": {},
48
  "tokenizer_class": "LlamaTokenizer",
 
25
  "special": true
26
  },
27
  "3": {
28
+ "content": "<pad>",
29
  "lstrip": false,
30
  "normalized": false,
31
  "rstrip": false,
 
33
  "special": true
34
  }
35
  },
 
 
 
36
  "bos_token": "<s>",
37
  "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 %}",
38
  "clean_up_tokenization_spaces": false,
39
  "eos_token": "</s>",
40
  "legacy": false,
41
  "model_max_length": 1000000000000000019884624838656,
42
+ "pad_token": "<pad>",
43
  "padding_side": "right",
44
  "sp_model_kwargs": {},
45
  "tokenizer_class": "LlamaTokenizer",