Visual Question Answering with Llama 3.2 HuggingFace

				
					[label llama-webapp/app.py]
import os
import requests
from PIL import Image
from flask import Flask, request, render_template, session
from transformers import MllamaForConditionalGeneration, AutoProcessor
import boto3
import torch
import re

app = Flask(__name__)
app.secret_key = "your-secure-random-key"

model_id = "meta-llama/Llama-3.2-11B-Vision-Instruct"
model = MllamaForConditionalGeneration.from_pretrained(
 model_id,
 torch_dtype=torch.bfloat16,
 device_map="auto",
)
processor = AutoProcessor.from_pretrained(model_id)

SPACE_NAME = "gpupro"
SPACE_REGION = "nyc3"
ACCESS_KEY = "your-access-key"
SECRET_KEY = "your-secret-key"

s3 = boto3.client(
 "s3",
 region_name=SPACE_REGION,
 endpoint_url=f"images/visual-questions-answering-llama-huggingface-transformers-section-1.png",
 aws_access_key_id=ACCESS_KEY,
 aws_secret_access_key=SECRET_KEY
)

def clean_text(text):
 text = re.sub(r"<\[^\>]+\>", "", text)
 text = re.sub(r"(?i)^(user|assistant):", "", text)
 text = re.sub(r"^\\\*+|\n\\\*+|\n-+|^-+", " ", text, flags=re.MULTILINE)
 text = re.sub(r"\s{2,}", " ", text).strip()
 return text

@app.route("/", methods=["GET", "POST"])
def index():
 result = None
 image_url = session.get("image_url")
 if request.method == "POST":
 prompt = request.form["prompt"]
 image_file = request.files.get("image")
 if image_file:
 filename = image_file.filename
 image_path = os.path.join("/tmp", filename)
 image_file.save(image_path)
 s3.upload_file(
 image_path,
 SPACE_NAME,
 filename,
 ExtraArgs={'ACL': 'public-read'}
 )
 image_url = f"images/visual-questions-answering-llama-huggingface-transformers-section-1.png}"
 session["image_url"] = image_url
 if not image_url:
 result = "Please upload an image to generate a description."
 else:
 image = Image.open(requests.get(image_url, stream=True).raw)
 messages = [{"role": "user", "content": [
 {"type": "image"},
 {"type": "text", "text": prompt}
 ]}]
 input_text = processor.apply_chat_template(messages, add_generation_prompt=True)
 inputs = processor(image, input_text, return_tensors="pt").to(model.device)
 output = model.generate(**inputs, max_new_tokens=28000)
 raw_result = processor.decode(output[0])
 result = clean_text(raw_result)
 if not result:
 result = "No description was generated. Please try again."
 return render_template("index.html", result=result, image_url=image_url)

if __name__ == "__main__":
 app.run(host="0.0.0.0", port=5000)