Upload tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +0 -1
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -62,7 +62,6 @@
|
|
| 62 |
"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 %}",
|
| 63 |
"clean_up_tokenization_spaces": false,
|
| 64 |
"eos_token": "<|endoftext|>",
|
| 65 |
-
"extra_special_tokens": {},
|
| 66 |
"model_max_length": 8192,
|
| 67 |
"tokenizer_class": "GPT2Tokenizer",
|
| 68 |
"unk_token": "<|endoftext|>",
|
|
|
|
| 62 |
"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 %}",
|
| 63 |
"clean_up_tokenization_spaces": false,
|
| 64 |
"eos_token": "<|endoftext|>",
|
|
|
|
| 65 |
"model_max_length": 8192,
|
| 66 |
"tokenizer_class": "GPT2Tokenizer",
|
| 67 |
"unk_token": "<|endoftext|>",
|