Update README.md

README.md

@@ -84,11 +84,16 @@ ds = load_dataset("mgoin/ultrachat_2k", split="train_sft").select(range(512))
 examples = [tokenizer.apply_chat_template(batch["messages"], tokenize=False) for batch in ds]
 examples = tokenizer(examples, padding=True, truncation=True, return_tensors="pt").to("cuda")
 
-quantize_config = BaseQuantizeConfig(quant_method="fp8", activation_scheme="static")
+quantize_config = BaseQuantizeConfig(
+    quant_method="fp8",
+    activation_scheme="dynamic",  # or "static"
+    ignore_patterns=["re:.*lm_head"],
+)
 
 model = AutoFP8ForCausalLM.from_pretrained(
     pretrained_model_dir, quantize_config=quantize_config
 )
+
 model.quantize(examples)
 model.save_quantized(quantized_model_dir)
 ```