adding docker configuration

Dockerfile

@@ -0,0 +1,36 @@
+# Use Python 3.12 as the base image
+FROM python:3.12
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    ffmpeg \
+    git \
+    && rm -rf /var/lib/apt/lists/*
+
+# Create a non-root user
+RUN useradd -m -u 1000 user
+WORKDIR /app
+
+# Install Python dependencies directly
+RUN pip install --no-cache-dir --upgrade pip && \
+    pip install --no-cache-dir \
+        torch \
+        torchvision \
+        git+https://github.com/huggingface/transformers \
+        accelerate \
+        qwen-vl-utils[decord]==0.0.8 \
+        fastapi \
+        uvicorn[standard] 
+
+# Copy application files
+COPY --chown=user . /app
+
+# Switch to the non-root user
+USER user
+
+# Set environment variables
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+
+# Command to run the application
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

main.py

@@ -0,0 +1,48 @@
+from fastapi import FastAPI, Query
+from transformers import Qwen2_5_VLForConditionalGeneration, AutoProcessor
+from qwen_vl_utils import process_vision_info
+import torch
+
+app = FastAPI()
+
+checkpoint = "Qwen/Qwen2.5-VL-3B-Instruct"
+min_pixels = 256*28*28
+max_pixels = 1280*28*28
+processor = AutoProcessor.from_pretrained(
+    checkpoint,
+    min_pixels=min_pixels,
+    max_pixels=max_pixels
+)
+model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
+    checkpoint,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+    # attn_implementation="flash_attention_2",
+)
+
+@app.get("/")
+def read_root():
+    return {"message": "API is live. Use the /predict endpoint."}
+
+@app.get("/predict")
+def predict(image_url: str = Query(...), prompt: str = Query(...)):
+    messages = [
+        {"role": "system", "content": "You are a helpful assistant with vision abilities."},
+        {"role": "user", "content": [{"type": "image", "image": image_url}, {"type": "text", "text": prompt}]},
+    ]
+    text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+    image_inputs, video_inputs = process_vision_info(messages)
+    inputs = processor(
+        text=[text],
+        images=image_inputs,
+        videos=video_inputs,
+        padding=True,
+        return_tensors="pt",
+    ).to(model.device)
+    with torch.no_grad():
+        generated_ids = model.generate(**inputs, max_new_tokens=128)
+    generated_ids_trimmed = [out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
+    output_texts = processor.batch_decode(
+        generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
+    )
+    return {"response": output_texts[0]}

model.py

@@ -0,0 +1,17 @@
+import requests
+
+url = "https://<uname>-<spacename>.hf.space/predict"
+
+# Define the parameters
+params = {
+    "image_url": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
+    "prompt": "describe",
+}
+
+# Send the GET request
+response = requests.get(url, params=params)
+
+if response.status_code == 200:
+    print("Response:", response.json())
+else:
+    print("Error:", response.status_code, response.text)