henilp105 commited on
Commit
1724e55
·
verified ·
1 Parent(s): 2f7ff46

Upload tokenizer

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +2 -3
tokenizer_config.json CHANGED
@@ -1,6 +1,4 @@
1
  {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
  "bos_token": {
5
  "__type": "AddedToken",
6
  "content": "<s>",
@@ -9,6 +7,7 @@
9
  "rstrip": false,
10
  "single_word": false
11
  },
 
12
  "clean_up_tokenization_spaces": false,
13
  "eos_token": {
14
  "__type": "AddedToken",
@@ -19,7 +18,7 @@
19
  "single_word": false
20
  },
21
  "legacy": false,
22
- "model_max_length": 4096,
23
  "pad_token": null,
24
  "padding_side": "right",
25
  "sp_model_kwargs": {},
 
1
  {
 
 
2
  "bos_token": {
3
  "__type": "AddedToken",
4
  "content": "<s>",
 
7
  "rstrip": false,
8
  "single_word": false
9
  },
10
+ "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 %}",
11
  "clean_up_tokenization_spaces": false,
12
  "eos_token": {
13
  "__type": "AddedToken",
 
18
  "single_word": false
19
  },
20
  "legacy": false,
21
+ "model_max_length": 1000000000000000019884624838656,
22
  "pad_token": null,
23
  "padding_side": "right",
24
  "sp_model_kwargs": {},