woodchen7 commited on
Commit
3bd2bcf
1 Parent(s): 68cba0d

Upload tokenizer_config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +13 -0
tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_max_length": 1048576,
3
+ "tokenizer_class": "HYTokenizer",
4
+ "auto_map": {
5
+ "AutoTokenizer": [
6
+ "tokenization_hy.HYTokenizer",
7
+ null
8
+ ]
9
+ },
10
+ "additional_special_tokens": ["<|startoftext|>", "<|extra_0|>", "<|extra_4|>", "<|extra_5|>", "<|eos|>"],
11
+ "chat_template": "{% set context = {'has_head': true} %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = message['content'] %}{% if loop.index0 == 0 %}{% if content == '' %}{% set _ = context.update({'has_head': false}) %}{% else %}{% set content = '<|startoftext|>' + content + '<|extra_4|>' %}{% endif %}{% endif %}{% if message['role'] == 'user' %}{% if loop.index0 == 1 and not context.has_head %}{% set content = '<|startoftext|>' + content %}{% endif %}{% if loop.index0 == 1 and context.has_head %}{% set content = content + '<|extra_0|>' %}{% else %}{% set content = '<|startoftext|>' + content + '<|extra_0|>' %}{% endif %}{% elif message['role'] == 'assistant' %}{% set content = content + '<|eos|>' %}{% endif %}{{ content }}{% endfor %}"
12
+ }
13
+