tamil-800m-instruct / tokenizer_config.json
skyblanket's picture
Initial release: experimental SFT chat version
6209bea verified
Raw
History Blame Contribute Delete
310 Bytes
{
"backend": "tokenizers",
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"is_local": true,
"local_files_only": false,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"tokenizer_class": "TokenizersBackend",
"unk_token": "<unk>"
}