lodrick-the-lafted commited on
Commit
76033d0
1 Parent(s): 2834ecc

Update tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +3 -9
tokenizer_config.json CHANGED
@@ -2052,19 +2052,13 @@
2052
  "bos_token": "<|begin_of_text|>",
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": 64,
2057
  "model_input_names": [
2058
  "input_ids",
2059
  "attention_mask"
2060
  ],
2061
- "model_max_length": 1000000000000000019884624838656,
2062
- "pad_to_multiple_of": null,
2063
  "pad_token": "<|end_of_text|>",
2064
- "pad_token_type_id": 0,
2065
  "padding_side": "left",
2066
- "stride": 0,
2067
- "tokenizer_class": "PreTrainedTokenizerFast",
2068
- "truncation_side": "right",
2069
- "truncation_strategy": "longest_first"
2070
  }
 
2052
  "bos_token": "<|begin_of_text|>",
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": "<|end_of_text|>",
 
2056
  "model_input_names": [
2057
  "input_ids",
2058
  "attention_mask"
2059
  ],
2060
+ "model_max_length": 8192,
 
2061
  "pad_token": "<|end_of_text|>",
 
2062
  "padding_side": "left",
2063
+ "tokenizer_class": "PreTrainedTokenizerFast"
 
 
 
2064
  }