artemgoncarov commited on
Commit
9a35cea
·
verified ·
1 Parent(s): 02d0290

Upload tokenizer

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +5 -1
tokenizer_config.json CHANGED
@@ -2053,6 +2053,7 @@
2053
  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
  "clean_up_tokenization_spaces": true,
2055
  "eos_token": "<|eot_id|>",
 
2056
  "model_input_names": [
2057
  "input_ids",
2058
  "attention_mask"
@@ -2060,5 +2061,8 @@
2060
  "model_max_length": 8192,
2061
  "pad_token": "<|eot_id|>",
2062
  "padding_side": "right",
2063
- "tokenizer_class": "PreTrainedTokenizerFast"
 
 
 
2064
  }
 
2053
  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
2054
  "clean_up_tokenization_spaces": true,
2055
  "eos_token": "<|eot_id|>",
2056
+ "max_length": 2048,
2057
  "model_input_names": [
2058
  "input_ids",
2059
  "attention_mask"
 
2061
  "model_max_length": 8192,
2062
  "pad_token": "<|eot_id|>",
2063
  "padding_side": "right",
2064
+ "stride": 0,
2065
+ "tokenizer_class": "PreTrainedTokenizerFast",
2066
+ "truncation_side": "right",
2067
+ "truncation_strategy": "longest_first"
2068
  }