Update app.py

app.py

@@ -3,7 +3,7 @@ from peft import PeftModel, PeftConfig
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
 peft_model_id = f"Bsbell21/llm_instruction_generator"
-model = AutoModelForCausalLM.from_pretrained(peft_model_id, return_dict=True, load_in_8bit=True, device_map='auto')
+model = AutoModelForCausalLM.from_pretrained(peft_model_id, return_dict=True, load_in_8bit=True, load_in_8bit_fp32_cpu_offload=True, device_map='auto')
 tokenizer = AutoTokenizer.from_pretrained(peft_model_id)
 # Load the Lora model
 # model = PeftModel.from_pretrained(model, peft_model_id)