c-tokenizer / tokenizer_config.json
elephantmipt's picture
Upload tokenizer
871b958
{
"add_bos_token": false,
"add_prefix_space": false,
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"errors": "replace",
"model_max_length": 2048,
"pad_token": null,
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}