fix: bad xinference error (#2384)

api/core/model_runtime/model_providers/xinference/llm/llm.py

                 elif 'generate' in extra_param.model_ability:
                     credentials['completion_type'] = 'completion'
                 else:
-                    raise ValueError(f'xinference model ability {extra_param.model_ability} is not supported')
+                    raise ValueError(f'xinference model ability {extra_param.model_ability} is not supported, check if you have the right model type')
                 
             if extra_param.support_function_call:
                 credentials['support_function_call'] = True

api/core/model_runtime/model_providers/xinference/text_embedding/text_embedding.py

                 credentials['max_tokens'] = extra_args.max_tokens
 
             self._invoke(model=model, credentials=credentials, texts=['ping'])
-        except (InvokeAuthorizationError, RuntimeError):
-            raise CredentialsValidateFailedError('Invalid api key')
+        except InvokeAuthorizationError as e:
+            raise CredentialsValidateFailedError(f'Failed to validate credentials for model {model}: {e}')
+        except RuntimeError as e:
+            raise CredentialsValidateFailedError(e)
 
     @property
     def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]: