dbmdz
/

convbert-base-turkish-mc4-uncased

Model card Files Files and versions

convbert-base-turkish-mc4-uncased / tokenizer_config.json

stefan-it's picture

tokenizer: add config (no accent stripping) and vocab

3450591 almost 5 years ago

History Blame Contribute Delete

82 Bytes

	{"do_lower_case": true, "max_len": 512, "init_inputs": [], "strip_accents":false}