Update README.md

README.md

@@ -50,11 +50,11 @@ device = "cuda"
 bolmo = AutoModelForCausalLM.from_pretrained("allenai/Bolmo-7B", trust_remote_code=True).to(device)
 tokenizer = AutoTokenizer.from_pretrained("allenai/Bolmo-7B", trust_remote_code=True)
 
-message = ["Who would win in a fight - a dinosaur or a cow named Moo Moo?"]
+message = ["Language modeling is "]
 input_ids = tokenizer(message, return_tensors="pt")["input_ids"].to(device)
 
 # `max_new_tokens` is the amuont of bytes to generate
-response = bolmo.generate(input_ids, max_new_tokens=100, do_sample=True)
+response = bolmo.generate(input_ids, max_new_tokens=256, do_sample=True, temperature=0.1)
 print(tokenizer.decode(response[0], skip_special_tokens=True))
 ```