Update README.md

README.md

@@ -118,7 +118,7 @@ prepare_for_inference(model, backend=backend, verbose=False)
 ############################################################
 #Generate (streaming)
 from hqq.utils.generation_hf import HFGenerator
-gen = HFGenerator(model, tokenizer, max_new_tokens=8192, do_sample=True, compile='partial').warmup()
+gen = HFGenerator(model, tokenizer, max_new_tokens=4096, do_sample=True, compile='partial').warmup()
 
 prompt = "If A equals B, and C equals B - A, what would be the value of C?" 
 out    = gen.generate(prompt, print_tokens=True)