Upload folder using huggingface_hub

Test_RAG.py

@@ -282,13 +282,6 @@ print(f"Loading model from {model_dir}")
 
 ov_config = {"PERFORMANCE_HINT": "LATENCY", "NUM_STREAMS": "1", "CACHE_DIR": ""}
 
-if "GPU" in llm_device and "qwen2-7b-instruct" in llm_model_id:
-    ov_config["GPU_ENABLE_SDPA_OPTIMIZATION"] = "NO"
-
-# On a GPU device a model is executed in FP16 precision. For red-pajama-3b-chat model there known accuracy
-# issues caused by this, which we avoid by setting precision hint to "f32".
-if llm_model_id == "red-pajama-3b-chat" and "GPU" in core.available_devices and llm_device in ["GPU", "AUTO"]:
-    ov_config["INFERENCE_PRECISION_HINT"] = "f32"
 
 # llm = HuggingFacePipeline.from_model_id(
 #     model_id= "meta-llama/Meta-Llama-3-8B",                                                                        
@@ -304,7 +297,7 @@ if llm_model_id == "red-pajama-3b-chat" and "GPU" in core.available_devices and
 # )
 from optimum.intel.openvino import OVModelForCausalLM
 from transformers import pipeline
-
+print("starting setting llm model")
 
 model_id = "meta-llama/Meta-Llama-3-8B"
 ov_config = {"PERFORMANCE_HINT": "LATENCY"}  # 这是一个例子，检查你的实际 ov_config