verbose/tokenizer_config.json
366 B · 15 lines · json Raw
1 {
2 "add_prefix_space": false,
3 "backend": "tokenizers",
4 "bos_token": "<s>",
5 "clean_up_tokenization_spaces": false,
6 "eos_token": "<|im_end|>",
7 "errors": "replace",
8 "is_local": true,
9 "model_max_length": 1000000000000000019884624838656,
10 "pad_token": "<|im_end|>",
11 "padding_side": "left",
12 "tokenizer_class": "GPT2Tokenizer",
13 "unk_token": "<unk>"
14 }
15