guj-grammar-base / tokenizer_config.json
Jayveersinh-Raj's picture
base 500k samples 4 epochs total (checkpoint trained)
71d43e1
raw
history blame
No virus
411 Bytes
{
"additional_special_tokens": null,
"clean_up_tokenization_spaces": true,
"eos_token": "</s>",
"extra_ids": 0,
"legacy": true,
"max_length": 128,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"sp_model_kwargs": {},
"stride": 0,
"tokenizer_class": "T5Tokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "<unk>"
}