correct model name, and add use_safetensors=False in from_quanted

web_quant.py

@@ -9,7 +9,7 @@ import gradio as gr
 from threading import Thread
 
 def load_model(model_name):
-    model = AutoGPTQForCausalLM.from_quantized(model_name, device_map="auto")
+    model = AutoGPTQForCausalLM.from_quantized(model_name, device_map="auto", use_safetensors=False)
     tokenizer = AutoTokenizer.from_pretrained(model_name, padding_side="right", use_fast=False)
     return model, tokenizer
     
@@ -108,6 +108,6 @@ def main(args):
 
 if __name__ == '__main__':
     parser = argparse.ArgumentParser()
-    parser.add_argument("--model-name", type=str, default="FreedomIntelligence/AceGPT-7B-chat-GPTQ")
+    parser.add_argument("--model-name", type=str, default="FreedomIntelligence/AceGPT-7b-chat-GPTQ")
     args = parser.parse_args()
     main(args)