Upload README.md with huggingface_hub

README.md

@@ -117,9 +117,9 @@ print("content:", content)
 
 Install the required packages:
 ```Shell
+pip install torch
 pip install git+https://github.com/huggingface/transformers@main
 pip install --pre torchao --index-url https://download.pytorch.org/whl/nightly/cu126
-pip install torch
 pip install accelerate
 ```
 
@@ -135,12 +135,12 @@ model_to_quantize = "google/gemma-3-12b-it"
 
 
 from torchao.quantization import Int4WeightOnlyConfig
-quant_config = Int4WeightOnlyConfig(group_size=128, use_hqq=True)
+quant_config = Int4WeightOnlyConfig(group_size=128, int4_packing_format="tile_packed_to_4d", int4_choose_qparams_algorithm="hqq")
 quantization_config = TorchAoConfig(quant_type=quant_config)
-
 quantized_model = AutoModelForCausalLM.from_pretrained(model_to_quantize, device_map="auto", torch_dtype=torch.bfloat16, quantization_config=quantization_config)
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 
+
 # Push to hub
 USER_ID = "YOUR_USER_ID"
 MODEL_NAME = model_id.split("/")[-1]