platistil / tokenizer_config.json
sirr
End of training
f2472c7
raw
history blame contribute delete
261 Bytes
{
"add_prefix_space": false,
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"model_max_length": 1024,
"pad_to_multiple_of": 8,
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}