Upload tokenizer

added_tokens.json

@@ -37,6 +37,6 @@
   "                             ": 50259,
   "                              ": 50258,
   "                               ": 50257,
-  "<|im_end|>": 50296,
-  "<|im_start|>": 50295
+  "<|im_start|>": 50295,
+  "[PAD]": 50296
 }

special_tokens_map.json

@@ -7,13 +7,19 @@
     "single_word": false
   },
   "eos_token": {
-    "content": "<|im_end|>",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": "</s>",
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer.json

@@ -365,7 +365,7 @@
     },
     {
       "id": 50296,
-      "content": "<|im_end|>",
+      "content": "[PAD]",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,

tokenizer_config.json

@@ -322,7 +322,7 @@
       "special": false
     },
     "50296": {
-      "content": "<|im_end|>",
+      "content": "[PAD]",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -332,9 +332,9 @@
   },
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|im_end|>",
+  "eos_token": "<|endoftext|>",
   "model_max_length": 2048,
-  "pad_token": "</s>",
+  "pad_token": "[PAD]",
   "tokenizer_class": "CodeGenTokenizer",
   "unk_token": "<|endoftext|>"
 }