Upload tokenizer

special_tokens_map.json

@@ -1,15 +1,5 @@
 {
-  "additional_special_tokens": [
-    {
-      "content": "<N>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    }
-  ],
   "bos_token": "<|endoftext|>",
   "eos_token": "<|endoftext|>",
-  "pad_token": "<|endoftext|>",
   "unk_token": "<|endoftext|>"
 }

tokenizer_config.json

@@ -1,31 +1,19 @@
 {
   "add_prefix_space": false,
   "added_tokens_decoder": {
-    "50256": {
+    "0": {
       "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": true,
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "50257": {
-      "content": "<N>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
-  "additional_special_tokens": [
-    "<N>"
-  ],
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
-  "model_max_length": 512,
-  "pad_token": "<|endoftext|>",
+  "model_max_length": 1024,
   "tokenizer_class": "GPT2Tokenizer",
   "unk_token": "<|endoftext|>"
 }