update special token

git add tokenizer_config.json

tokenizer_config.json

@@ -5,46 +5,17 @@
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|endoftext|>",
   "errors": "replace",
-  "extra_special_tokens": [
-    "<|endoftext|>",
-    "<fim_prefix>",
-    "<fim_middle>",
-    "<fim_suffix>",
-    "<fim_pad>",
-    "<repo_name>",
-    "<file_sep>",
-    "<issue_start>",
-    "<issue_comment>",
-    "<issue_closed>",
-    "<jupyter_start>",
-    "<jupyter_text>",
-    "<jupyter_code>",
-    "<jupyter_output>",
-    "<jupyter_script>",
-    "<empty_output>",
-    "<code_to_intermediate>",
-    "<intermediate_to_code>",
-    "<pr>",
-    "<pr_status>",
-    "<pr_is_merged>",
-    "<pr_base>",
-    "<pr_file>",
-    "<pr_base_code>",
-    "<pr_diff>",
-    "<pr_diff_hunk>",
-    "<pr_comment>",
-    "<pr_event_id>",
-    "<pr_review>",
-    "<pr_review_state>",
-    "<pr_review_comment>",
-    "<pr_in_reply_to_review_id>",
-    "<pr_in_reply_to_comment_id>",
-    "<pr_diff_hunk_comment_line>",
-    "<NAME>",
-    "<EMAIL>",
-    "<KEY>",
-    "<PASSWORD>"
-  ],
+  "extra_special_tokens": {
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "tokenizer_class": "GPT2Tokenizer",
+  "vocab_size": 49152
+}
   "is_local": false,
   "local_files_only": false,
   "model_max_length": 1000000000000000019884624838656,