Update app.py

app.py

@@ -16,7 +16,7 @@ pipe = pipeline(
 )
 
 # Set gpu_layers to the number of layers to offload to GPU. Set to 0 if no GPU acceleration is available on your system.
-llm = AutoModelForCausalLM.from_pretrained("TheBloke/Mistral-7B-v0.1-GGUF", model_file="mistral-7b-v0.1.Q4_K_M.gguf", model_type="mistral", gpu_layers=0)
+llm = AutoModelForCausalLM.from_pretrained("TheBloke/Mistral-7B-v0.1-GGUF", model_file="mistral-7b-v0.1.Q4_K_M.gguf", model_type="mistral", gpu_layers=0, hf=True)
 tokenizer = AutoTokenizer.from_pretrained(llm)
 
 llm_pipe = pipeline("text-generation", model=llm, tokenizer=tokenizer)