youjunhyeok
commited on
Commit
•
bf47ceb
1
Parent(s):
fccc947
Upload tokenizer
Browse files- special_tokens_map.json +7 -1
- tokenizer_config.json +1 -1
special_tokens_map.json
CHANGED
@@ -13,7 +13,13 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
"unk_token": {
|
18 |
"content": "<unk>",
|
19 |
"lstrip": false,
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
"unk_token": {
|
24 |
"content": "<unk>",
|
25 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
@@ -85,7 +85,7 @@
|
|
85 |
}
|
86 |
},
|
87 |
"bos_token": "<s>",
|
88 |
-
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{
|
89 |
"clean_up_tokenization_spaces": false,
|
90 |
"eos_token": "</s>",
|
91 |
"legacy": true,
|
|
|
85 |
}
|
86 |
},
|
87 |
"bos_token": "<s>",
|
88 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message + '\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\nAssistant: ' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' + '\n' }}{% endif %}{% endfor %}",
|
89 |
"clean_up_tokenization_spaces": false,
|
90 |
"eos_token": "</s>",
|
91 |
"legacy": true,
|