Fix code genenration code format issue (#1424)

Signed-off-by: lvliang-intel <liang1.lv@intel.com>

Author: lvliang-intel

intel_extension_for_transformers/neural_chat/server/restful/codegen_api.py

@@ -100,7 +100,7 @@ def handle_chat_completion_request(self, request: ChatCompletionRequest):
                 def stream_generator():
                     nonlocal buffered_texts
                     for output in generator:
-                        yield f"data: {output}\n\n"
+                        yield f"data: {output.encode()}\n\n"
                     yield f"data: [DONE]\n\n"
                     if is_plugin_enabled("cache") and \
                        not plugins["cache"]["instance"].pre_llm_inference_actions(request.prompt):