Upload tokenizer

special_tokens_map.json

@@ -13,6 +13,7 @@
     "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": 500,
+    "strategy": "LongestFirst",
+    "stride": 0
+  },
+  "padding": {
+    "strategy": "BatchLongest",
+    "direction": "Left",
+    "pad_to_multiple_of": null,
+    "pad_id": 50256,
+    "pad_type_id": 0,
+    "pad_token": "<|endoftext|>"
+  },
   "added_tokens": [
     {
       "id": 50256,

tokenizer_config.json

@@ -317,8 +317,9 @@
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
-  "max_length": 1024,
+  "max_length": 250,
   "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
   "tokenizer_class": "CodeGenTokenizer",
   "unk_token": "<|endoftext|>"
 }