Lugaborg commited on
Commit
13edf83
1 Parent(s): efd8ee7

Upload tokenizer

Browse files
Files changed (2) hide show
  1. tokenizer.json +6 -1
  2. tokenizer_config.json +4 -0
tokenizer.json CHANGED
@@ -1,6 +1,11 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 2048,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
  "padding": null,
10
  "added_tokens": [
11
  {
tokenizer_config.json CHANGED
@@ -313,8 +313,12 @@
313
  "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 %}",
314
  "clean_up_tokenization_spaces": true,
315
  "eos_token": "<|endoftext|>",
 
316
  "model_max_length": 2048,
317
  "pad_token": "<|end_of_text|>",
 
318
  "tokenizer_class": "GPT2Tokenizer",
 
 
319
  "unk_token": "<|endoftext|>"
320
  }
 
313
  "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 %}",
314
  "clean_up_tokenization_spaces": true,
315
  "eos_token": "<|endoftext|>",
316
+ "max_length": 2048,
317
  "model_max_length": 2048,
318
  "pad_token": "<|end_of_text|>",
319
+ "stride": 0,
320
  "tokenizer_class": "GPT2Tokenizer",
321
+ "truncation_side": "right",
322
+ "truncation_strategy": "longest_first",
323
  "unk_token": "<|endoftext|>"
324
  }