use smaller model

app.py

@@ -20,12 +20,12 @@ os.environ["HF_HUB_ENABLE_HF_TRANSFER"] = "1"
 
 
 model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
-    "Qwen/Qwen2.5-VL-7B-Instruct",
+    "Qwen/Qwen2.5-VL-3B-Instruct",
     torch_dtype=torch.bfloat16,
     attn_implementation="flash_attention_2",
     device_map="auto",
 )
-processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct")
+processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-3B-Instruct")
 
 
 class GeneralRetrievalQuery(BaseModel):