Upload tokenizer_config.json
Browse files- tokenizer_config.json +13 -5
tokenizer_config.json
CHANGED
@@ -11,7 +11,7 @@
|
|
11 |
"special": true
|
12 |
},
|
13 |
"1": {
|
14 |
-
"content": "
|
15 |
"lstrip": false,
|
16 |
"normalized": false,
|
17 |
"rstrip": false,
|
@@ -851,7 +851,7 @@
|
|
851 |
"special": false
|
852 |
},
|
853 |
"106": {
|
854 |
-
"content": "
|
855 |
"lstrip": false,
|
856 |
"normalized": false,
|
857 |
"rstrip": false,
|
@@ -1995,12 +1995,20 @@
|
|
1995 |
"special": false
|
1996 |
}
|
1997 |
},
|
|
|
|
|
|
|
|
|
1998 |
"bos_token": "<bos>",
|
1999 |
-
"chat_template": "{% if 'role'
|
2000 |
"clean_up_tokenization_spaces": false,
|
2001 |
-
"eos_token": "
|
2002 |
"model_max_length": 1000000000000000019884624838656,
|
2003 |
"pad_token": "<pad>",
|
|
|
|
|
|
|
2004 |
"tokenizer_class": "GemmaTokenizer",
|
2005 |
-
"unk_token": "<unk>"
|
|
|
2006 |
}
|
|
|
11 |
"special": true
|
12 |
},
|
13 |
"1": {
|
14 |
+
"content": "<eos>",
|
15 |
"lstrip": false,
|
16 |
"normalized": false,
|
17 |
"rstrip": false,
|
|
|
851 |
"special": false
|
852 |
},
|
853 |
"106": {
|
854 |
+
"content": "<start_of_turn>",
|
855 |
"lstrip": false,
|
856 |
"normalized": false,
|
857 |
"rstrip": false,
|
|
|
1995 |
"special": false
|
1996 |
}
|
1997 |
},
|
1998 |
+
"additional_special_tokens": [
|
1999 |
+
"<start_of_turn>",
|
2000 |
+
"<end_of_turn>"
|
2001 |
+
],
|
2002 |
"bos_token": "<bos>",
|
2003 |
+
"chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
|
2004 |
"clean_up_tokenization_spaces": false,
|
2005 |
+
"eos_token": "<eos>",
|
2006 |
"model_max_length": 1000000000000000019884624838656,
|
2007 |
"pad_token": "<pad>",
|
2008 |
+
"padding_side": "left",
|
2009 |
+
"sp_model_kwargs": {},
|
2010 |
+
"spaces_between_special_tokens": false,
|
2011 |
"tokenizer_class": "GemmaTokenizer",
|
2012 |
+
"unk_token": "<unk>",
|
2013 |
+
"use_default_system_prompt": false
|
2014 |
}
|