Update README.md

README.md

@@ -174,27 +174,6 @@ output_text = tokenizer.batch_decode(
     generated_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False
 )
 print("Response:", output_text[0][len(prompt):])
-
-# Local Benchmark
-import torch.utils.benchmark as benchmark
-from torchao.utils import benchmark_model
-import torchao
-
-def benchmark_fn(f, *args, **kwargs):
-    # Manual warmup
-    for _ in range(2):
-        f(*args, **kwargs)
-
-    t0 = benchmark.Timer(
-        stmt="f(*args, **kwargs)",
-        globals={"args": args, "kwargs": kwargs, "f": f},
-        num_threads=torch.get_num_threads(),
-    )
-    return f"{(t0.blocked_autorange().mean):.3f}"
-
-torchao.quantization.utils.recommended_inductor_config_setter()
-quantized_model = torch.compile(quantized_model, mode="max-autotune")
-print(f"{save_to} model:", benchmark_fn(quantized_model.generate, **inputs, max_new_tokens=128))
 ```
 
 # Model Quality