pythia-1b-deduped-tldr-sft / tokenizer_config.json
edbeeching's picture
edbeeching HF staff
Add cleanrl/EleutherAI_pythia-1b-deduped__sft__tldr-main checkpoint
b4a250b verified
raw
history blame contribute delete
291 Bytes
{
"add_prefix_space": false,
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": true,
"eos_token": "<|endoftext|>",
"model_max_length": 1000000000000000019884624838656,
"padding_side": "right",
"tokenizer_class": "GPTNeoXTokenizer",
"unk_token": "<|endoftext|>"
}