Upload tokenizer

special_tokens_map.json

@@ -34,6 +34,7 @@
     "rstrip": false,
     "single_word": false
   },
+  "pad_token": "<|endoftext|>",
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer.json

@@ -1,7 +1,19 @@
 {
   "version": "1.0",
-  "truncation": null,
-  "padding": null,
+  "truncation": {
+    "direction": "Right",
+    "max_length": 1024,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Right",
+    "pad_to_multiple_of": null,
+    "pad_id": 0,
+    "pad_type_id": 0,
+    "pad_token": "<|endoftext|>"
+  },
   "added_tokens": [
     {
       "id": 0,

tokenizer_config.json

@@ -180,6 +180,7 @@
   "eos_token": "<|endoftext|>",
   "extra_special_tokens": {},
   "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>",
   "vocab_size": 49152