Upload tokenizer
Browse files- special_tokens_map.json +3 -3
- tokenizer_config.json +1 -1
special_tokens_map.json
CHANGED
|
@@ -3,12 +3,12 @@
|
|
| 3 |
"<|im_start|>",
|
| 4 |
"<|im_end|>"
|
| 5 |
],
|
| 6 |
-
"eos_token":
|
|
|
|
| 7 |
"content": "<|endoftext|>",
|
| 8 |
"lstrip": false,
|
| 9 |
"normalized": false,
|
| 10 |
"rstrip": false,
|
| 11 |
"single_word": false
|
| 12 |
-
}
|
| 13 |
-
"pad_token": "<|endoftext|>"
|
| 14 |
}
|
|
|
|
| 3 |
"<|im_start|>",
|
| 4 |
"<|im_end|>"
|
| 5 |
],
|
| 6 |
+
"eos_token": "<|im_end|>",
|
| 7 |
+
"pad_token": {
|
| 8 |
"content": "<|endoftext|>",
|
| 9 |
"lstrip": false,
|
| 10 |
"normalized": false,
|
| 11 |
"rstrip": false,
|
| 12 |
"single_word": false
|
| 13 |
+
}
|
|
|
|
| 14 |
}
|
tokenizer_config.json
CHANGED
|
@@ -33,7 +33,7 @@
|
|
| 33 |
"bos_token": null,
|
| 34 |
"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 %}",
|
| 35 |
"clean_up_tokenization_spaces": false,
|
| 36 |
-
"eos_token": "<|
|
| 37 |
"errors": "replace",
|
| 38 |
"model_max_length": 32768,
|
| 39 |
"pad_token": "<|endoftext|>",
|
|
|
|
| 33 |
"bos_token": null,
|
| 34 |
"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 %}",
|
| 35 |
"clean_up_tokenization_spaces": false,
|
| 36 |
+
"eos_token": "<|im_end|>",
|
| 37 |
"errors": "replace",
|
| 38 |
"model_max_length": 32768,
|
| 39 |
"pad_token": "<|endoftext|>",
|