Update README.md

README.md

@@ -26,7 +26,7 @@ On CUDA devices, the computation dtype is typically FP16 for int4 , which may le
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 
-quantized_model_dir = "/dataset/int4_models/DeepSeek-V3-int4-sym-gptq-inc-preview"
+quantized_model_dir = "OPEA/DeepSeek-V3-int4-sym-gptq-inc"
 
 ## directly use device_map='auto' if you have enough GPUs
 max_memory = {i: "75GiB" for i in range(7)}