Upload 2 files

app.py

@@ -0,0 +1,26 @@
+import gradio as gr
+from transformers import AutoProcessor, AutoModelForCausalLM
+import torch
+from PIL import Image
+
+MODEL_ID = "Qwen/Qwen1.5-VL-Chat"
+
+processor = AutoProcessor.from_pretrained(MODEL_ID, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(MODEL_ID, device_map="auto", trust_remote_code=True, torch_dtype=torch.bfloat16)
+
+def qwen_vl_chat(image, question):
+    inputs = processor(text=question, images=image, return_tensors="pt").to(model.device)
+    outputs = model.generate(**inputs, max_new_tokens=256)
+    answer = processor.batch_decode(outputs, skip_special_tokens=True)[0]
+    return answer
+
+demo = gr.Interface(
+    fn=qwen_vl_chat,
+    inputs=[gr.Image(type="pil"), gr.Textbox(label="请输入问题")],
+    outputs="text",
+    title="🧠 Qwen1.5-VL 图文问答 Demo",
+    description="上传一张图片，问一个问题，模型会给出答案。"
+)
+
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,5 @@
+torch
+transformers==4.38.2
+gradio==4.14.0
+accelerate
+transformers_stream_generator