grimjim commited on
Commit
d7660c9
1 Parent(s): b82d1f8

Reverted tokenizer

Browse files
Files changed (3) hide show
  1. tekken.json +3 -0
  2. tokenizer.json +2 -2
  3. tokenizer_config.json +4 -3
tekken.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eccd1665d2e477697c33cb7f0daa6f6dfefc57a0a6bceb66d4be52952f827516
3
+ size 14801223
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:868ad0021d8fcb7c1da1debcabd7443fccd21697a51abc03b3c1abb52c64b91e
3
- size 17078592
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e11c71726323d33da7b8d6f6f269f1988931c0a52b7122bcdd8c05042974e0db
3
+ size 9264445
tokenizer_config.json CHANGED
@@ -1,4 +1,6 @@
1
  {
 
 
2
  "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
  "0": {
@@ -8003,10 +8005,9 @@
8003
  }
8004
  },
8005
  "bos_token": "<s>",
8006
- "chat_template": "{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content'] %}\n {%- set loop_messages = messages[1:] %}\n{%- else %}\n {%- set loop_messages = messages %}\n{%- endif %}\n\n{{- bos_token }}\n{%- for message in loop_messages %}\n {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}\n {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}\n {%- endif %}\n {%- if message['role'] == 'user' %}\n {%- if loop.last and system_message is defined %}\n {{- '[INST] ' + system_message + '\\n\\n' + message['content'] + '[/INST]' }}\n {%- else %}\n {{- '[INST] ' + message['content'] + '[/INST]' }}\n {%- endif %}\n {%- elif message['role'] == 'assistant' %}\n {{- ' ' + message['content'] + eos_token}}\n {%- else %}\n {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}\n {%- endif %}\n{%- endfor %}\n",
8007
- "clean_up_tokenization_spaces": true,
8008
  "eos_token": "</s>",
8009
  "model_max_length": 1000000000000000019884624838656,
8010
- "tokenizer_class": "GPT2Tokenizer",
8011
  "unk_token": "<unk>"
8012
  }
 
1
  {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
  "add_prefix_space": false,
5
  "added_tokens_decoder": {
6
  "0": {
 
8005
  }
8006
  },
8007
  "bos_token": "<s>",
8008
+ "clean_up_tokenization_spaces": false,
 
8009
  "eos_token": "</s>",
8010
  "model_max_length": 1000000000000000019884624838656,
8011
+ "tokenizer_class": "PreTrainedTokenizerFast",
8012
  "unk_token": "<unk>"
8013
  }