hopefully no mle this time

app.py

@@ -11,7 +11,7 @@ class Assistant:
         device_map = 'auto'
         # bnb_config = BitsAndBytesConfig(load_in_4bit=True, bnb_4bit_quant_type="nf4",bnb_4bit_compute_dtype=torch.float16,)
         # self.model = AutoModelForCausalLM.from_pretrained( model_name,quantization_config=bnb_config, trust_remote_code=True,use_cache=False,device_map=device_map)
-        self.model = AutoModelForCausalLM.from_pretrained( model_name, trust_remote_code=True,use_cache=True,device_map=device_map)
+        self.model = AutoModelForCausalLM.from_pretrained( model_name, trust_remote_code=True,use_cache=False,device_map=device_map)
         
         self.tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
         self.tokenizer.pad_token = self.tokenizer.eos_token
@@ -49,4 +49,4 @@ demo = gr.ChatInterface(
 
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()

requirements.txt

@@ -2,7 +2,6 @@ accelerate==1.2.1
 aiofiles==23.2.1
 annotated-types==0.7.0
 anyio==4.7.0
-bitsandbytes==0.45.0
 certifi==2024.12.14
 charset-normalizer==3.4.1
 click==8.1.8