Update README.md

README.md

@@ -74,10 +74,10 @@ python quantize.py --model_path ibm-granite/granite-3.1-8b-instruct --quant_path
 
 ```python
 from datasets import load_dataset
-from transformers import AutoTokenizer
+from transformers import AutoTokenizer, AutoModelForCausalLM
 from llmcompressor.modifiers.quantization import GPTQModifier
 from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
-from llmcompressor.transformers import SparseAutoModelForCausalLM, oneshot, apply
+from llmcompressor.transformers import oneshot, apply
 import argparse
 from compressed_tensors.quantization import QuantizationScheme, QuantizationArgs, QuantizationType, QuantizationStrategy
 
@@ -90,7 +90,7 @@ parser.add_argument('--dampening_frac', type=float, default=0.1)
 parser.add_argument('--observer', type=str, default="minmax")
 args = parser.parse_args()
 
-model = SparseAutoModelForCausalLM.from_pretrained(
+model = AutoModelForCausalLM.from_pretrained(
     args.model_path,
     device_map="auto",
     torch_dtype="auto",