add tokenizer

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a3d8b13e81f1324c05ee2a010c2f9b49f4ceb5887da444843b6dddd035d8701
+size 17082828

tokenizer_config.json

@@ -1 +1 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "sp_model_kwargs": {}, "model_max_length": 512, "special_tokens_map_file": "input_models/johngiorgi-declutr-small-all-paraphrase-multilingual/0_Transformer/special_tokens_map.json", "full_tokenizer_file": null, "name_or_path": "/content/model_marketing_run_mlm", "tokenizer_class": "XLMRobertaTokenizer"}
+{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": "input_models/johngiorgi-declutr-small-all-paraphrase-multilingual/0_Transformer/special_tokens_map.json", "full_tokenizer_file": null, "name_or_path": "/content/model_marketing_run_mlm", "sp_model_kwargs": {}, "tokenizer_class": "XLMRobertaTokenizer"}