hiroki-rad commited on
Commit
3e683be
·
verified ·
1 Parent(s): 912cf0f

Upload tokenizer

Browse files
special_tokens_map.json CHANGED
@@ -1,4 +1,8 @@
1
  {
 
 
 
 
2
  "bos_token": {
3
  "content": "<bos>",
4
  "lstrip": false,
 
1
  {
2
+ "additional_special_tokens": [
3
+ "<start_of_turn>",
4
+ "<end_of_turn>"
5
+ ],
6
  "bos_token": {
7
  "content": "<bos>",
8
  "lstrip": false,
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c36fea8c2ad69ed08c6180b465a70bf23e9bde2453632f9d3ba827383154def
3
- size 34362885
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f7eee611703c5ce5d1eee32d9cdcfe465647b8aff0c1dfb3bed7ad7dbb05060
3
+ size 34362873
tokenizer.model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6969e64047744a44bb3abfb5c50f8de0f7ed8b571d5444426ef931f651d1a0ef
3
- size 4241111
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
3
+ size 4241003
tokenizer_config.json CHANGED
@@ -1987,7 +1987,7 @@
1987
  "special": false
1988
  },
1989
  "255999": {
1990
- "content": "<start_of_image>",
1991
  "lstrip": false,
1992
  "normalized": false,
1993
  "rstrip": false,
@@ -1995,8 +1995,11 @@
1995
  "special": false
1996
  }
1997
  },
 
 
 
 
1998
  "bos_token": "<bos>",
1999
- "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 %}",
2000
  "clean_up_tokenization_spaces": false,
2001
  "eos_token": "<eos>",
2002
  "model_max_length": 1000000000000000019884624838656,
 
1987
  "special": false
1988
  },
1989
  "255999": {
1990
+ "content": "<unused99>",
1991
  "lstrip": false,
1992
  "normalized": false,
1993
  "rstrip": false,
 
1995
  "special": false
1996
  }
1997
  },
1998
+ "additional_special_tokens": [
1999
+ "<start_of_turn>",
2000
+ "<end_of_turn>"
2001
+ ],
2002
  "bos_token": "<bos>",
 
2003
  "clean_up_tokenization_spaces": false,
2004
  "eos_token": "<eos>",
2005
  "model_max_length": 1000000000000000019884624838656,