dbmdz
/

convbert-base-turkish-mc4-uncased

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

tokenizer: add config (no accent stripping) and vocab

3450591 over 2 years ago

No virus

82 Bytes

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