Update README.md

README.md

@@ -25,6 +25,8 @@ Please refer to the AWQ quantization license ([link](https://github.com/llm-awq/
 
 This model was successfully tested on CUDA driver v530.30.02 and runtime v11.7 with Python v3.10.11. Please note that AWQ requires NVIDIA GPUs with compute capability of 80 or higher.
 
+For Docker users, the `nvcr.io/nvidia/pytorch:23.06-py3` image is runtime v12.1 but otherwise the same as the configuration above and has also been verified to work.
+
 ## How to Use
 
 ```bash
@@ -61,7 +63,7 @@ q_config = {
 load_quant = hf_hub_download('abhinavkulkarni/mpt-7b-chat-w4-g128-awq', 'pytorch_model.bin')
 
 with init_empty_weights():
-    model = AutoModelForCausalLM.from_pretrained(model_name, config=config, 
+    model = AutoModelForCausalLM.from_config(config=config, 
                                                  torch_dtype=torch.float16, trust_remote_code=True)
 
 real_quantize_model_weight(model, w_bit=w_bit, q_config=q_config, init_only=True)