Upload 2 files
Browse files- tokenizer_config.json +5 -13
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,
|
|
@@ -1995,20 +1995,12 @@
|
|
| 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": "{
|
| 2004 |
"clean_up_tokenization_spaces": false,
|
| 2005 |
-
"eos_token": "
|
| 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 |
}
|
|
|
|
| 11 |
"special": true
|
| 12 |
},
|
| 13 |
"1": {
|
| 14 |
+
"content": "<|im_end|>",
|
| 15 |
"lstrip": false,
|
| 16 |
"normalized": false,
|
| 17 |
"rstrip": false,
|
|
|
|
| 851 |
"special": false
|
| 852 |
},
|
| 853 |
"106": {
|
| 854 |
+
"content": "<|im_start|>",
|
| 855 |
"lstrip": false,
|
| 856 |
"normalized": false,
|
| 857 |
"rstrip": false,
|
|
|
|
| 1995 |
"special": false
|
| 1996 |
}
|
| 1997 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1998 |
"bos_token": "<bos>",
|
| 1999 |
+
"chat_template": "{% if 'role' in messages[0] %}{{ bos_token }}{% for message in messages %}{% if message['role'] == 'user' %}{{'<|im_start|>user\n' + message['content'] + '<|im_end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|im_start|>assistant\n' + message['content'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['content'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}{% else %}{{ bos_token }}{% for message in messages %}{% if message['from'] == 'human' %}{{'<|im_start|>user\n' + message['value'] + '<|im_end|>\n'}}{% elif message['from'] == 'gpt' %}{{'<|im_start|>assistant\n' + message['value'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['value'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}{% endif %}",
|
| 2000 |
"clean_up_tokenization_spaces": false,
|
| 2001 |
+
"eos_token": "<|im_end|>",
|
| 2002 |
"model_max_length": 1000000000000000019884624838656,
|
| 2003 |
"pad_token": "<pad>",
|
|
|
|
|
|
|
|
|
|
| 2004 |
"tokenizer_class": "GemmaTokenizer",
|
| 2005 |
+
"unk_token": "<unk>"
|
|
|
|
| 2006 |
}
|