titu_lm_55gb_72k / tokenizer_config.json
muntasir2000's picture
Update tokenizer_config.json
ad15617
raw history blame
No virus
363 Bytes
{
"auto_map": {
"AutoTokenizer": ["tokenization_bn.BNTokenizer", null]
},
"tokenizer_class": "BNTokenizer",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"model_max_length": 2048,
"pad_token": "<|reserved001|>",
"padding_side": "right",
"sep_token": null,
"sp_model_kwargs": {},
"unk_token": "<unk>"
}