Upload tokenizer

special_tokens_map.json

@@ -19,7 +19,13 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<unk>",
+  "pad_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -170,6 +170,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
+    "ignore_merges": false,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,

tokenizer_config.json

@@ -72,9 +72,9 @@
   "fill_token": "<FILL_ME>",
   "legacy": null,
   "middle_token": "▁<MID>",
-  "model_max_length": 16384,
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<unk>",
-  "padding_side": "right",
+  "padding_side": "left",
   "prefix_token": "▁<PRE>",
   "sp_model_kwargs": {},
   "suffix_token": "▁<SUF>",