kreyol-mt-scratch-pubtrain / tokenizer_config.json
n8rob's picture
Upload folder using huggingface_hub
7662722 verified
raw
history blame contribute delete
533 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": true, "__type": "AddedToken"}, "use_fast": false, "strip_accents": false, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "/share03/draj/data/parallel_corpora/creole/creolemt/naacl/albert-allpublic64k"}