AWA-50M-Tokenizer-V1 / tokenizer_config.json
tampakwill's picture
Upload folder using huggingface_hub
e30bfc9 verified
raw
history blame contribute delete
314 Bytes
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": "<s>",
"eos_token": "</s>",
"errors": "replace",
"is_local": true,
"mask_token": "<mask>",
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<unk>"
}