Update README.md

README.md

@@ -33,10 +33,10 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
 model_id = "BiMediX/BiMediX-Bi"
 
 tokenizer = AutoTokenizer.from_pretrained(model_id)
-model = AutoModelForCausalLM.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")
 
 text = "Hello BiMediX! I've been experiencing increased tiredness in the past week."
-inputs = tokenizer(text, return_tensors="pt")
+inputs = tokenizer(text, return_tensors="pt").to('cuda')
 
 outputs = model.generate(**inputs, max_new_tokens=500)
 print(tokenizer.decode(outputs[0], skip_special_tokens=True))