Add application file

app.py

@@ -0,0 +1,89 @@
+import gradio as gr
+from transformers import AutoProcessor, Qwen2_5_VLForConditionalGeneration, TextIteratorStreamer
+from transformers.image_utils import load_image
+from threading import Thread
+import time
+import torch
+import spaces
+
+MODEL_ID = "Qwen/Qwen2-VL-2B-Instruct"
+processor = AutoProcessor.from_pretrained(MODEL_ID, trust_remote_code=True)
+model = Qwen2_VLForConditionalGeneration.from_pretrained(
+    MODEL_ID,
+    trust_remote_code=True,
+    torch_dtype=torch.bfloat16
+).to("cpu").eval()
+
+@spaces.GPU
+def model_inference(input_dict, history):
+    text = input_dict["text"]
+    files = input_dict["files"]
+
+    # Load images if provided
+    if len(files) > 1:
+        images = [load_image(image) for image in files]
+    elif len(files) == 1:
+        images = [load_image(files[0])]
+    else:
+        images = []
+
+    # Validate input
+    if text == "" and not images:
+        gr.Error("Please input a query and optionally image(s).")
+        return
+    if text == "" and images:
+        gr.Error("Please input a text query along with the image(s).")
+        return
+
+    # Prepare messages for the model
+    messages = [
+        {
+            "role": "user",
+            "content": [
+                *[{"type": "image", "image": image} for image in images],
+                {"type": "text", "text": text},
+            ],
+        }
+    ]
+
+    # Apply chat template and process inputs
+    prompt = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+    inputs = processor(
+        text=[prompt],
+        images=images if images else None,
+        return_tensors="pt",
+        padding=True,
+    ).to("cpu")
+
+    # Set up streamer for real-time output
+    streamer = TextIteratorStreamer(processor, skip_prompt=True, skip_special_tokens=True)
+    generation_kwargs = dict(inputs, streamer=streamer, max_new_tokens=1024)
+
+    # Start generation in a separate thread
+    thread = Thread(target=model.generate, kwargs=generation_kwargs)
+    thread.start()
+
+    # Stream the output
+    buffer = ""
+    yield "Thinking..."
+    for new_text in streamer:
+        buffer += new_text
+        time.sleep(0.01)
+        yield buffer
+
+
+# Example inputs
+examples = [
+]
+
+demo = gr.ChatInterface(
+    fn=model_inference,
+    description="# **Qwen2-VL-2B-Instruct**",
+    examples=examples,
+    textbox=gr.MultimodalTextbox(label="Query Input", file_types=["image"], file_count="multiple"),
+    stop_btn="Stop Generation",
+    multimodal=True,
+    cache_examples=False,
+)
+
+demo.launch(debug=True)

requirements.txt

@@ -0,0 +1,8 @@
+gradio_client==1.3.0
+qwen-vl-utils==0.0.2
+transformers-stream-generator==0.0.4
+torch==2.4.0
+torchvision==0.19.0
+git+https://github.com/huggingface/transformers.git
+accelerate
+av