sam-paech commited on
Commit
e168654
1 Parent(s): 0aecf7a

Upload 4 files

Browse files
Files changed (3) hide show
  1. tokenizer.json +2 -2
  2. tokenizer.model +3 -0
  3. tokenizer_config.json +2 -2
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 sha256:3f289bc05132635a8bc7aca7aa21255efd5e18f3710f43e3cdb96bcd41be4922
3
+ size 17525357
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
3
+ size 4241003
tokenizer_config.json CHANGED
@@ -2000,10 +2000,10 @@
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'] == '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": 2048,
2007
  "pad_token": "<pad>",
2008
  "padding_side": "left",
2009
  "sp_model_kwargs": {},
 
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": 1000000000000000019884624838656,
2007
  "pad_token": "<pad>",
2008
  "padding_side": "left",
2009
  "sp_model_kwargs": {},