Update app.py

app.py

@@ -15,7 +15,8 @@ from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
 
 quantization_config = BitsAndBytesConfig(llm_int8_enable_fp32_cpu_offload=True)
 tok = AutoTokenizer.from_pretrained("stabilityai/stablelm-tuned-alpha-3b", device_map="auto", load_in_8bit=True, torch_dtype=torch.float16 )
-m = AutoModelForCausalLM.from_pretrained("stabilityai/stablelm-tuned-alpha-3b", device_map= "auto", quantization_config=quantization_config)
+m = AutoModelForCausalLM.from_pretrained("stabilityai/stablelm-tuned-alpha-3b", device_map= "auto", quantization_config=quantization_config,
+                                        offload_folder="./")
 generator = pipeline('text-generation', model=m, tokenizer=tok, device=0)
 print(f"Sucessfully loaded the model to the memory")