Upload tokenizer

special_tokens_map.json

@@ -17,12 +17,6 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "<|endoftext|>",
-  "unk_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "pad_token": "<|PAD_TOKEN|>",
+  "unk_token": "�"
 }

tokenizer.json

@@ -155,6 +155,15 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 49152,
+      "content": "<|PAD_TOKEN|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": null,

tokenizer_config.json

@@ -136,6 +136,14 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "49152": {
+      "content": "<|PAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "additional_special_tokens": [
@@ -147,9 +155,9 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "model_max_length": 2048,
-  "pad_token": "<|endoftext|>",
+  "pad_token": "<|PAD_TOKEN|>",
   "padding_side": "left",
   "tokenizer_class": "GPT2Tokenizer",
-  "unk_token": "<|endoftext|>",
+  "unk_token": "�",
   "vocab_size": 49152
 }