Update README.md

README.md

@@ -6,7 +6,7 @@ base_model:
 ---
 ## Model Details
 
-This model is an int4 model(The vision module has also been quantized) with group_size 128 and symmetric quantization of [deepseek-ai/deepseek-vl2](https://huggingface.co/deepseek-ai/deepseek-vl2) generated by [intel/auto-round](https://github.com/intel/auto-round).
+This model is an int4 model(The vision module has also been quantized) with group_size 128 and symmetric quantization of [deepseek-ai/deepseek-vl2](https://huggingface.co/deepseek-ai/deepseek-vl2) generated by [intel/auto-round](https://github.com/intel/auto-round). Load the model with revision ```2e595e8``` to use AutoGPTQ format.
 
 ## How to Use
 ### INT4 Inference
@@ -25,7 +25,13 @@ model_path = "OPEA/deepseek-vl2-int4-sym-inc"
 vl_chat_processor: DeepseekVLV2Processor = DeepseekVLV2Processor.from_pretrained(model_path)
 tokenizer = vl_chat_processor.tokenizer
 
-vl_gpt: DeepseekVLV2ForCausalLM = AutoModelForCausalLM.from_pretrained(model_path, trust_remote_code=True, device_map="auto", torch_dtype="auto")
+vl_gpt: DeepseekVLV2ForCausalLM = AutoModelForCausalLM.from_pretrained(
+  model_path,
+  trust_remote_code=True,
+  device_map="auto",
+  torch_dtype="auto",
+  ## revision="2e595e8" ##AutoGPTQ format
+)
 vl_gpt = vl_gpt.eval()
 
 image_url = "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg"