Upload tokenizer

added_tokens.json

@@ -36,8 +36,5 @@
   "                            ": 50260,
   "                             ": 50259,
   "                              ": 50258,
-  "                               ": 50257,
-  "<PAD>": 50296,
-  "<|im_end|>": 50297,
-  "<|im_start|>": 50295
+  "                               ": 50257
 }

special_tokens_map.json

@@ -7,19 +7,12 @@
     "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": true,
-    "rstrip": false,
-    "single_word": false
-  },
   "unk_token": {
     "content": "<|endoftext|>",
     "lstrip": false,

tokenizer_config.json

@@ -312,38 +312,13 @@
       "rstrip": false,
       "single_word": false,
       "special": false
-    },
-    "50295": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": false
-    },
-    "50296": {
-      "content": "<PAD>",
-      "lstrip": false,
-      "normalized": true,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "50297": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
   "bos_token": "<|endoftext|>",
-  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "<|im_end|>",
+  "eos_token": "<|endoftext|>",
   "model_max_length": 2048,
-  "pad_token": "<PAD>",
+  "return_token_type_ids": false,
   "tokenizer_class": "CodeGenTokenizer",
   "unk_token": "<|endoftext|>"
 }