Update README.md

README.md

@@ -66,7 +66,7 @@ MODEL_NAME = 'Kukedlc/NeuralStockFusion-7b'
 tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
 model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, device_map='cuda:0', quantization_config=bnb_config)
 
-inputs = tokenizer(["What is a large language model, in spanish\n\n"], return_tensors="pt").to('cuda')
+inputs = tokenizer(["[INST] What is a large language model, in spanish \n[/INST]\n"], return_tensors="pt").to('cuda')
 streamer = TextStreamer(tokenizer)
 
 # Despite returning the usual output, the streamer will also print the generated text to stdout.