add tokenizer

.gitattributes

@@ -30,3 +30,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

sentencepiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67ce12ea4550e57af39217a75686a61695e34edbb1c9892f82f0b861d73a4482
+size 4697711

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc9763ae434157a06eed04e8aed33be549503d7478fdf049213e7db71dc0090a
+size 16709845

tokenizer_config.json

@@ -0,0 +1 @@
+{"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"}, "model_max_length": 256, "special_tokens_map_file": "/root/.cache/huggingface/transformers/d0d5cf448e7367ce69a8cbb48980c788a66b736ec136a0d3061fd26b5c1b25f0.f886166424e457f0fc75f92e81205faabe843b2dbbbef6b25f9d8ec69f64bc7d", "name_or_path": "rembert-german-qa", "tokenizer_class": "RemBertTokenizer"}