Update app.py

app.py

@@ -66,13 +66,16 @@ from langchain_huggingface import HuggingFaceEndpoint, ChatHuggingFace
 # repo_id = "Qwen/Qwen2.5-7B-Instruct"
 # repo_id = "google/gemma-2-2b-it"
 # repo_id = "mistralai/Mistral-7B-Instruct-v0.3"
-repo_id = "HuggingFaceTB/SmolLM2-1.7B-Instruct"
+# repo_id = "HuggingFaceTB/SmolLM2-1.7B-Instruct"
+repo_id = "microsoft/Phi-3.5-mini-instruct"
+
 
 llm = HuggingFaceEndpoint(
     repo_id=repo_id,
     task="text-generation",
     max_new_tokens=512,
     huggingfacehub_api_token=os.getenv("HF_TOKEN"),
+    model_kwargs={"wait_for_model": True}
 )
 
 # 2. ChatHuggingFace will correctly route this to the /v1/chat/completions