Instructblip Flan T5 Xl 8bit

🚀 InstructBLIP model

The InstructBLIP model uses Flan - T5-xl as its language model, aiming to solve vision - language tasks and bring value to related fields.

🚀 Quick Start

The InstructBLIP model is a powerful tool for vision - language tasks. It combines a vision model with a language model to generate text descriptions based on images.

✨ Features

• Uses Flan - T5-xl as the language model.
• It is a visual instruction - tuned version of BLIP - 2.
• Introduced in the paper InstructBLIP: Towards General - purpose Vision - Language Models with Instruction Tuning by Dai et al.

📚 Documentation

Model description

InstructBLIP is a visual instruction tuned version of BLIP - 2. Refer to the paper for details.

Intended uses & limitations

Usage is as follows:

from transformers import InstructBlipProcessor, InstructBlipForConditionalGeneration
import torch
from PIL import Image
import requests

model = InstructBlipForConditionalGeneration.from_pretrained("Salesforce/instructblip-flan-t5-xl")
processor = InstructBlipProcessor.from_pretrained("Salesforce/instructblip-flan-t5-xl")

device = "cuda" if torch.cuda.is_available() else "cpu"
model.to(device)

url = "https://raw.githubusercontent.com/salesforce/LAVIS/main/docs/_static/Confusing-Pictures.jpg"
image = Image.open(requests.get(url, stream=True).raw).convert("RGB")
prompt = "What is unusual about this image?"
inputs = processor(images=image, text=prompt, return_tensors="pt").to(device)

outputs = model.generate(
        **inputs,
        do_sample=False,
        num_beams=5,
        max_length=256,
        min_length=1,
        top_p=0.9,
        repetition_penalty=1.5,
        length_penalty=1.0,
        temperature=1,
)
generated_text = processor.batch_decode(outputs, skip_special_tokens=True)[0].strip()
print(generated_text)

How to use

For code examples, we refer to the documentation.

📄 License

This model is released under the MIT license.