dbmdz
/

electra-base-turkish-mc4-uncased-discriminator

Transformers PyTorch TensorFlow

Turkish electra pretraining Inference Endpoints

Model card Files Files and versions Community

electra-base-turkish-mc4-uncased-discriminator / tokenizer_config.json

stefan-it's picture

tokenizer add config (no accent stripping) and vocab

2c19cbc over 2 years ago

raw history blame contribute delete

No virus

82 Bytes

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