Update app.py

app.py

@@ -59,8 +59,9 @@ retriever = db.as_retriever(
 model_name = "Daemontatox/CogitoZ14"  # Replace with your desired model
 tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", trust_remote_code=True)
-@spaces.GPU()
-hf_pipeline = pipeline("text-generation")
+
+# Create Hugging Face Pipeline with the specified model and tokenizer
+hf_pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
 # LangChain LLM using Hugging Face Pipeline
 llm = HuggingFacePipeline(pipeline=hf_pipeline)
@@ -121,4 +122,4 @@ interface = gr.Interface(
 
 # Launch Gradio app
 if __name__ == "__main__":
-    interface.launch()
+    interface.launch()