feat: disable token counting in large language models for performance testing

Signed-off-by: -LAN- <laipz8200@outlook.com>

api/core/model_runtime/model_providers/__base/large_language_model.py

@@ -537,7 +537,6 @@ if you are not sure about the structure.
         """
         raise NotImplementedError
 
-    @abstractmethod
     def get_num_tokens(
         self,
         model: str,
@@ -554,7 +553,8 @@ if you are not sure about the structure.
         :param tools: tools for tool calling
         :return:
         """
-        raise NotImplementedError
+        # Disable the token count in LLMs for profermance testing.
+        return 0
 
     def enforce_stop_tokens(self, text: str, stop: list[str]) -> str:
         """Cut off the text as soon as any stop words occur."""

api/core/model_runtime/model_providers/__base/tokenizers/gpt2_tokenzier.py

@@ -25,8 +25,7 @@ class GPT2Tokenizer:
         # future = _executor.submit(GPT2Tokenizer._get_num_tokens_by_gpt2, text)
         # result = future.result()
         # return cast(int, result)
-        # return GPT2Tokenizer._get_num_tokens_by_gpt2(text)
+        return GPT2Tokenizer._get_num_tokens_by_gpt2(text)
-        return 0
 
     @staticmethod
     def get_encoder() -> Any: