Update tokenizer_config.json
Browse files- tokenizer_config.json +2 -1
tokenizer_config.json
CHANGED
@@ -2051,6 +2051,7 @@
|
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
2053 |
"chat_template": "{{bos_token}}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
|
|
2054 |
"eos_token": "<|im_end|>",
|
2055 |
"model_input_names": [
|
2056 |
"input_ids",
|
@@ -2059,4 +2060,4 @@
|
|
2059 |
"model_max_length": 131072,
|
2060 |
"pad_token": "<|end_of_text|>",
|
2061 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2062 |
-
}
|
|
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
2053 |
"chat_template": "{{bos_token}}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
2054 |
+
"clean_up_tokenization_spaces": true,
|
2055 |
"eos_token": "<|im_end|>",
|
2056 |
"model_input_names": [
|
2057 |
"input_ids",
|
|
|
2060 |
"model_max_length": 131072,
|
2061 |
"pad_token": "<|end_of_text|>",
|
2062 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2063 |
+
}
|