hienbm commited on
Commit
69ddd03
·
verified ·
1 Parent(s): a653e40

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 sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
3
- size 34362873
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abd905f70a0604065e2115e2e99a985ae7f6c42a528cb9e0ac42c1178c6fc151
3
+ size 34362971
tokenizer_config.json CHANGED
@@ -2000,7 +2000,7 @@
2000
  "<end_of_turn>"
2001
  ],
2002
  "bos_token": "<bos>",
2003
- "chat_template": "{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
2004
  "clean_up_tokenization_spaces": false,
2005
  "eos_token": "<eos>",
2006
  "model_max_length": 8192,
 
2000
  "<end_of_turn>"
2001
  ],
2002
  "bos_token": "<bos>",
2003
+ "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
2004
  "clean_up_tokenization_spaces": false,
2005
  "eos_token": "<eos>",
2006
  "model_max_length": 8192,