Update app.py

app.py

@@ -25,8 +25,8 @@ API_TOKEN = os.getenv('HF_INFER_API')
 @st.cache_resource
 def get_llm_chain():
     return custom_chain_with_history(
-        llm=CustomLLM(repo_id="AdaptLLM/medicine-chat", model_type='text-generation', api_token=API_TOKEN, temperature=0.001), 
-        # llm=CustomLLM(repo_id="google/gemma-7b", model_type='text-generation', api_token=API_TOKEN, stop=["\n<|","<|"], temperature=0.001), 
+        # llm=CustomLLM(repo_id="AdaptLLM/medicine-chat", model_type='text-generation', api_token=API_TOKEN, temperature=0.001), 
+        llm=CustomLLM(repo_id="google/gemma-7b", model_type='text-generation', api_token=API_TOKEN, stop=["\n<|","<|"], temperature=0.001), 
         # memory=st.session_state.memory.chat_memory,
         memory=st.session_state.memory
     )