Update README.md

README.md

@@ -68,11 +68,12 @@ model = AutoModelForCausalLM.from_pretrained(MODEL_NAME, device_map='cuda:0', lo
 tok = AutoTokenizer.from_pretrained(MODEL_NAME)
 
 # Inference
-inputs = tok(["I want you to generate a theory that unites quantum mechanics with the theory of relativity and cosmic consciousness"], return_tensors="pt").to('cuda')
+prompt = "I want you to generate a theory that unites quantum mechanics with the theory of relativity and cosmic consciousness\n"
+inputs = tok([prompt], return_tensors="pt").to('cuda')
 streamer = TextStreamer(tok)
 
 # Despite returning the usual output, the streamer will also print the generated text to stdout.
-_ = model.generate(**inputs, streamer=streamer, max_new_tokens=512)
+_ = model.generate(**inputs, streamer=streamer, max_new_tokens=512, do_sample=True, num_beams=1, top_p=0.9, temperature=0.7)
 
 ```
 ## 💻 Usage - Clasic