update exmple

examples/quantization_w4a16/llama3_example.py

@@ -6,6 +6,7 @@
 
 # Select model and load it.
 MODEL_ID = "meta-llama/Meta-Llama-3-8B-Instruct"
+MODEL_ID = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
 model = SparseAutoModelForCausalLM.from_pretrained(
     MODEL_ID,
     device_map="auto",
@@ -54,7 +55,6 @@ def tokenize(sample):
 
 # Configure the quantization algorithm to run.
 #   * quantize the weights to 4 bit with GPTQ with a group size 128
-# Note: to reduce GPU memory use `sequential_update=False`
 recipe = GPTQModifier(targets="Linear", scheme="W4A16", ignore=["lm_head"])
 
 # Apply algorithms.