whizzzzkid commited on
Commit
6bd7476
1 Parent(s): 557e6c2

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +2 -2
  2. tokenizer_config.json +2 -2
tokenizer.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:631fbd6e3f9415c226372013d876a6a5106009bb2637021ea2b73d524163dd5c
3
- size 4239425
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:404910d171d502ee02e19adeb54760c129c2a924aadeebff74f59d3f4099a193
3
+ size 4239453
tokenizer_config.json CHANGED
@@ -302,10 +302,10 @@
302
  "<|extra0|>"
303
  ],
304
  "bos_token": "<|endoftext|>",
305
- "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|system|>\\n' + system_message + '<|endoftext|>' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|user|>\\n' + content + '<|endoftext|>' + '\\n<|assistant|>\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '\\n' }}{% endif %}{% endfor %}",
306
  "clean_up_tokenization_spaces": true,
307
  "eos_token": "<|endoftext|>",
308
- "model_max_length": 2048,
309
  "pad_token": "<|endoftext|>",
310
  "tokenizer_class": "GPT2Tokenizer",
311
  "unk_token": "<|endoftext|>"
 
302
  "<|extra0|>"
303
  ],
304
  "bos_token": "<|endoftext|>",
305
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
306
  "clean_up_tokenization_spaces": true,
307
  "eos_token": "<|endoftext|>",
308
+ "model_max_length": 4096,
309
  "pad_token": "<|endoftext|>",
310
  "tokenizer_class": "GPT2Tokenizer",
311
  "unk_token": "<|endoftext|>"