pythia-70m-deduped-cleansharegpt-en / tokenizer_config.json
CaterinaLac's picture
Upload 6 files
6071aa3
raw
history blame contribute delete
264 Bytes
{
"add_prefix_space": false,
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"model_max_length": 1000000000000000019884624838656,
"tokenizer_class": "GPTNeoXTokenizer",
"unk_token": "<|endoftext|>"
}