Upload tokenizer

special_tokens_map.json

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

tokenizer_config.json

@@ -205,8 +205,12 @@
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
+  "max_length": 1024,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<|endoftext|>",
+  "stride": 0,
   "tokenizer_class": "GPTNeoXTokenizer",
+  "truncation_side": "left",
+  "truncation_strategy": "longest_first",
   "unk_token": "<|endoftext|>"
 }