imsuprtwo2 commited on
Commit
bd6065f
·
verified ·
1 Parent(s): 5f5d556

Upload tokenizer

Browse files
Files changed (3) hide show
  1. chat_template.jinja +1 -0
  2. tokenizer.json +0 -0
  3. tokenizer_config.json +12 -0
chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ {% 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 %}
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<s>",
4
+ "clean_up_tokenization_spaces": false,
5
+ "eos_token": "</s>",
6
+ "is_local": false,
7
+ "model_max_length": 2048,
8
+ "pad_token": "</s>",
9
+ "sp_model_kwargs": {},
10
+ "tokenizer_class": "TokenizersBackend",
11
+ "unk_token": "<unk>"
12
+ }