BaoHuynh2002 commited on
Commit
d762cbc
1 Parent(s): cd6568c

Upload tokenizer

Browse files
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "</s>",
5
+ "unk_token": "<unk>"
6
+ }
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
+ "add_prefix_space": false,
3
+ "bos_token": "<s>",
4
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{% if message['role'] == 'user' and loop.first %}{{ '### Câu hỏi: ' + message['content'].strip() }}{% elif message['role'] == 'user' %}{{ '\n### Câu hỏi: ' + message['content'].strip() }}{% elif message['role'] == 'assistant' %}{{ '\n### Trả lời: ' + message['content'] + eos_token }}{% endif %}{% if loop.last %}{% if message['role'] == 'user' and add_generation_prompt %}{{ '\n### Trả lời:' }}{% endif %}{% endif %}{% endfor %}",
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "</s>",
7
+ "model_max_length": 8192,
8
+ "pad_token": "<pad>",
9
+ "padding_side": "right",
10
+ "tokenizer_class": "BloomTokenizer",
11
+ "unk_token": "<unk>"
12
+ }