OpenSML-150M / tokenizer /tokenizer_config.json
wzebrowski's picture
Add training records, tokenizer, configurations and evaluations
7708682 verified
Raw History Blame Contribute Delete
200 Bytes
{
"add_bos_token": false,
"add_eos_token": false,
"clean_up_tokenization_spaces": false,
"eos_token": "<|doc_end|>",
"pad_token": "<|pad|>",
"tokenizer_class": "PreTrainedTokenizerFast"
}