bloomz-7b1-mt-org-prune / tokenizer_config.json
coincheung's picture
remove some of vocab from original
4f40e62
{
"add_bos_token": true,
"add_eos_token": true,
"add_prefix_space": false,
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"padding_side": "left",
"tokenizer_class": "BloomTokenizer",
"unk_token": "<unk>"
}