Upload tokenizer

sentencepiece.bpe.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
-size 5069051
+oid sha256:34e9d938fbab77d2bb4acd48953c66bb7ad2d0b675b4c0911e6ed25caf20acd6
+size 1270564

special_tokens_map.json

@@ -5,7 +5,7 @@
   "mask_token": {
     "content": "<mask>",
     "lstrip": true,
-    "normalized": false,
+    "normalized": true,
     "rstrip": false,
     "single_word": false
   },

tokenizer_config.json

@@ -11,12 +11,10 @@
     "rstrip": false,
     "single_word": false
   },
-  "model_max_length": 512,
-  "name_or_path": "intfloat/multilingual-e5-large",
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "sp_model_kwargs": {},
-  "special_tokens_map_file": "/home/jovyan/.cache/huggingface/hub/models--intfloat--multilingual-e5-large/snapshots/c505dce3578a12ec54e47bdc72bef5cd0eacb085/special_tokens_map.json",
   "tokenizer_class": "XLMRobertaTokenizer",
   "unk_token": "<unk>"
 }