Update rag_demo/rag/retriever.py

rag_demo/rag/retriever.py

@@ -112,7 +112,7 @@ class RAGPipeline:
             context += "\n Document: "
             context += chunk.content
         api = InferenceClient(
-            model="meta-llama/Llama-3.1-8B-Instruct",
+            model="Qwen/Qwen2.5-72B-Instruct",
             token=os.getenv("HF_API_TOKEN"),
         )
         answer_generation_template = AnswerGenerationTemplate()