Aira-2-portuguese-1B7 / tokenizer_config.json
nicholasKluge's picture
Upload 10 files
285f749
raw history blame
No virus
308 Bytes
{
"add_prefix_space": true,
"bos_token": "<|startoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<|pad|>",
"padding_side": "left",
"tokenizer_class": "BloomTokenizer",
"unk_token": "<unk>"
}