Overwrite `tokenizer_config.json` with the one from the original repository
Browse files- tokenizer_config.json +3 -3
tokenizer_config.json
CHANGED
|
@@ -50,13 +50,13 @@
|
|
| 50 |
}
|
| 51 |
},
|
| 52 |
"additional_special_tokens": [],
|
| 53 |
-
"bos_token": "
|
| 54 |
"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 %}",
|
| 55 |
"clean_up_tokenization_spaces": false,
|
| 56 |
-
"eos_token": "
|
| 57 |
"legacy": true,
|
| 58 |
"max_length": 1536,
|
| 59 |
-
"model_max_length":
|
| 60 |
"pad_token": "[PAD]",
|
| 61 |
"sp_model_kwargs": {},
|
| 62 |
"spaces_between_special_tokens": false,
|
|
|
|
| 50 |
}
|
| 51 |
},
|
| 52 |
"additional_special_tokens": [],
|
| 53 |
+
"bos_token": "<s>",
|
| 54 |
"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 %}",
|
| 55 |
"clean_up_tokenization_spaces": false,
|
| 56 |
+
"eos_token": "</s>",
|
| 57 |
"legacy": true,
|
| 58 |
"max_length": 1536,
|
| 59 |
+
"model_max_length": 4096,
|
| 60 |
"pad_token": "[PAD]",
|
| 61 |
"sp_model_kwargs": {},
|
| 62 |
"spaces_between_special_tokens": false,
|