Update tokenizer_config.json (#3)
Browse files- Update tokenizer_config.json (3c81cd23bdfff827b48923f58d30e0b9bd4cb994)
Co-authored-by: Tiezhen WANG <[email protected]>
- tokenizer_config.json +1 -1
tokenizer_config.json
CHANGED
|
@@ -4,7 +4,7 @@
|
|
| 4 |
"clean_up_tokenization_spaces": false,
|
| 5 |
"eos_token": "<|endoftext|>",
|
| 6 |
"model_max_length": 8192,
|
| 7 |
-
"tokenizer_class": "
|
| 8 |
"unk_token": "<|endoftext|>",
|
| 9 |
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
|
| 10 |
}
|
|
|
|
| 4 |
"clean_up_tokenization_spaces": false,
|
| 5 |
"eos_token": "<|endoftext|>",
|
| 6 |
"model_max_length": 8192,
|
| 7 |
+
"tokenizer_class": "GPT2TokenizerFast",
|
| 8 |
"unk_token": "<|endoftext|>",
|
| 9 |
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"
|
| 10 |
}
|