PRIMERA-100-MDS / tokenizer_config.json
cammy's picture
Training in progress, epoch 1
8344194
{"unk_token": {"content": "<unk>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "add_prefix_space": false, "errors": "replace", "sep_token": {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "cls_token": {"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": {"content": "<pad>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "trim_offsets": true, "model_max_length": 4096, "special_tokens_map_file": "C:\\Users\\User/.cache\\huggingface\\transformers\\11580dbf54b49da2d44191726dd2ed18e1ed26a495b393512201f5822711c62b.0e55ca6797ff34881d64b92cd1563c7e5dbfccac3b6235e6923625abd01fb78b", "name_or_path": "allenai/PRIMERA", "tokenizer_class": "LEDTokenizer"}