CMA-20M / tokenizer_config.json
User01110's picture
Evaluated step 2000: WikiText BPB 1.3592
6e07d52 verified
Raw
History Blame Contribute Delete
254 Bytes
{
"backend": "tokenizers",
"bos_token": "<|bos|>",
"eos_token": "<|eos|>",
"is_local": false,
"local_files_only": false,
"model_max_length": 1024,
"pad_token": "<|pad|>",
"tokenizer_class": "TokenizersBackend",
"unk_token": "<|unk|>"
}