Diksha2001 commited on
Commit
7ed5be9
·
verified ·
1 Parent(s): d0effda

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +2 -2
  2. tokenizer_config.json +1 -1
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1f4a1a7159f2dacfa01410288c1b9faee8d5e309c880cb3dfc8e9ab3e070cef
3
- size 17209915
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad1a901e03b7b08be930d1e1642e79a89ad4f6c086f82643b381b8d30da164a6
3
+ size 9085652
tokenizer_config.json CHANGED
@@ -2051,7 +2051,7 @@
2051
  },
2052
  "bos_token": "<|begin_of_text|>",
2053
  "chat_template": "{% if 'role' in messages[0] %}{% for message in messages %}{% if message['role'] == 'user' %}{{'<|im_start|>user\n' + message['content'] + '<|im_end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|im_start|>assistant\n' + message['content'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['content'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}{% else %}{% for message in messages %}{% if message['from'] == 'human' %}{{'<|im_start|>user\n' + message['value'] + '<|im_end|>\n'}}{% elif message['from'] == 'gpt' %}{{'<|im_start|>assistant\n' + message['value'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['value'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}{% endif %}",
2054
- "clean_up_tokenization_spaces": false,
2055
  "eos_token": "<|im_end|>",
2056
  "model_max_length": 1000000000000000019884624838656,
2057
  "pad_token": "<|finetune_right_pad_id|>",
 
2051
  },
2052
  "bos_token": "<|begin_of_text|>",
2053
  "chat_template": "{% if 'role' in messages[0] %}{% for message in messages %}{% if message['role'] == 'user' %}{{'<|im_start|>user\n' + message['content'] + '<|im_end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|im_start|>assistant\n' + message['content'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['content'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}{% else %}{% for message in messages %}{% if message['from'] == 'human' %}{{'<|im_start|>user\n' + message['value'] + '<|im_end|>\n'}}{% elif message['from'] == 'gpt' %}{{'<|im_start|>assistant\n' + message['value'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['value'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}{% endif %}",
2054
+ "clean_up_tokenization_spaces": true,
2055
  "eos_token": "<|im_end|>",
2056
  "model_max_length": 1000000000000000019884624838656,
2057
  "pad_token": "<|finetune_right_pad_id|>",