xlmindic-base-multiscript / tokenizer_config.json

xlmindic-base-multiscript tokenizer, model weights (in Pytorch, TF and Flax) and tags

f974d3f almost 5 years ago

423 Bytes

{"do_lower_case": false, "remove_space": true, "keep_accents": true, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false, "__type": "AddedToken"}, "sp_model_kwargs": {}, "model_max_length": 512, "tokenizer_class": "AlbertTokenizer"}