bloomy-64k-sv-only-tokenizer / tokenizer_config.json
robinq's picture
Upload tokenizer
4d918b0
raw
history blame
257 Bytes
{
"add_prefix_space": true,
"bos_token": "<s>",
"clean_up_tokenization_spaces": true,
"eos_token": "</s>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<unk>"
}