Update app.py

app.py

@@ -98,40 +98,4 @@ if model_loaded:
 
         # Display GPU memory information after generation
         gpu_memory_after_generation = get_gpu_memory()
-        st.write(f"GPU Memory Info after generation: {gpu_memory_after_generation}")
-
-tokenizer = AutoTokenizer.from_pretrained(local_folder, use_fast=False)
-
-quantize_config = BaseQuantizeConfig(
-        bits=4,
-        group_size=128,
-        desc_act=False
-    )
-
-model = AutoGPTQForCausalLM.from_quantized(local_folder,
-        use_safetensors=True,
-        strict=use_strict,
-        model_basename=model_basename,
-        device="cuda:0",
-        use_triton=use_triton,
-        quantize_config=quantize_config)
-
-pipe = pipeline(
-    "text-generation",
-    model=model,
-    tokenizer=tokenizer,
-    max_new_tokens=512,
-    temperature=0.1,
-    top_p=0.95,
-    repetition_penalty=1.15
-)
-
-user_input = st.text_input("Input a phrase")
-
-prompt_template=f'''USER: {user_input}
-ASSISTANT:'''
-
-# Generate output when the "Generate" button is pressed
-if st.button("Generate the prompt"):
-    output = pipe(prompt_template)[0]['generated_text']
-    st.text_area("Prompt", value=output)
+        st.write(f"GPU Memory Info after generation: {gpu_memory_after_generation}")