Instructblip Flan T5 Xl

🚀 InstructBLIP model

The InstructBLIP model uses Flan - T5-xl as its language model, aiming to address vision - language tasks.

🚀 Quick Start

The InstructBLIP model is a remarkable advancement in the field of vision - language processing. It utilizes Flan - T5-xl as its language model, offering powerful capabilities for various vision - related tasks.

✨ Features

• Based on BLIP - 2: InstructBLIP is a visual instruction tuned version of [BLIP - 2](https://huggingface.co/docs/transformers/main/model_doc/blip - 2), which enhances its performance in vision - language tasks.
• Research - Oriented: This release is mainly for research purposes to support an academic paper.

📚 Documentation

Model description

InstructBLIP is a visual instruction tuned version of [BLIP - 2](https://huggingface.co/docs/transformers/main/model_doc/blip - 2). For detailed information, please refer to the paper InstructBLIP: Towards General - purpose Vision - Language Models with Instruction Tuning by Dai et al.

Intended uses & limitations

The usage example 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 more code examples, please refer to the documentation.

Ethical Considerations

This release is for research purposes only in support of an academic paper. Our models, datasets, and code are not specifically designed or evaluated for all downstream purposes. We strongly recommend users evaluate and address potential concerns related to accuracy, safety, and fairness before deploying this model. We encourage users to consider the common limitations of AI, comply with applicable laws, and leverage best practices when selecting use cases, particularly for high - risk scenarios where errors or misuse could significantly impact people’s lives, rights, or safety. For further guidance on use cases, refer to our AUP and AI AUP.

📄 License

This model is released under the MIT license.