Update app.py

app.py

@@ -20,11 +20,12 @@ path = "OpenGVLab/InternVL2_5-4B"
 model = AutoModel.from_pretrained(
     path,
     cache_dir=cache_folder,
-    torch_dtype=torch.bfloat16 if torch.cuda.is_available() else torch.float32,
+    torch_dtype=torch.bfloat16,,
+    load_in_8bit=True,
     low_cpu_mem_usage=True,
     use_flash_attn=True,
     trust_remote_code=True
-).eval().to("cpu")
+).eval()
 
 tokenizer = AutoTokenizer.from_pretrained(
     path,