Upload tokenizer

special_tokens_map.json

@@ -23,6 +23,7 @@
     "rstrip": false,
     "single_word": false
   },
+  "pad_token": "</s>",
   "unk_token": {
     "content": "<unk>",
     "lstrip": false,

tokenizer.json

@@ -1,7 +1,19 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 2048,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 2,
+    "pad_type_id": 0,
+    "pad_token": "</s>"
+  },
   "added_tokens": [
     {
       "id": 0,

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5441161d140f285cab44391cd047f31b4fa04e6ed3409996f055d95de80da70c
-size 131
+oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
+size 500058

tokenizer_config.json

@@ -77,7 +77,8 @@
   "legacy": null,
   "middle_token": "▁<MID>",
   "model_max_length": 1000000000000000019884624838656,
-  "pad_token": null,
+  "pad_token": "</s>",
+  "padding_side": "right",
   "prefix_token": "▁<PRE>",
   "sp_model_kwargs": {},
   "suffix_token": "▁<SUF>",