Upload tokenizer

special_tokens_map.json

@@ -12,5 +12,12 @@
     ">>SUFFIX<<",
     ">>MIDDLE<<"
   ],
-  "eos_token": "<|endoftext|>"
+  "eos_token": "<|endoftext|>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer.json

@@ -110,6 +110,15 @@
       "rstrip": false,
       "normalized": false,
       "special": true
+    },
+    {
+      "id": 65024,
+      "content": "<pad>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
     }
   ],
   "normalizer": null,

tokenizer_config.json

@@ -96,6 +96,14 @@
       "rstrip": false,
       "single_word": false,
       "special": true
+    },
+    "65024": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
     }
   },
   "additional_special_tokens": [
@@ -117,6 +125,7 @@
     "input_ids",
     "attention_mask"
   ],
-  "model_max_length": 2048,
+  "model_max_length": 4096,
+  "pad_token": "<pad>",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }