whizzzzkid commited on
Commit
b04759d
1 Parent(s): 8fb7c26

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +1 -6
  2. tokenizer_config.json +1 -5
tokenizer.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 4096,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
tokenizer_config.json CHANGED
@@ -302,15 +302,11 @@
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
- "max_length": 4096,
309
  "model_max_length": 2048,
310
  "pad_token": "<|endoftext|>",
311
- "stride": 0,
312
  "tokenizer_class": "GPT2Tokenizer",
313
- "truncation_side": "right",
314
- "truncation_strategy": "longest_first",
315
  "unk_token": "<|endoftext|>"
316
  }
 
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|>"
312
  }