# InstructBLIP
## Overview
The InstructBLIP model was proposed in [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://arxiv.org/abs/2305.06500) by Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, Steven Hoi.
InstructBLIP leverages the [BLIP-2](blip2) architecture for visual instruction tuning.
The abstract from the paper is the following:
*General-purpose language models that can solve various language-domain tasks have emerged driven by the pre-training and instruction-tuning pipeline. However, building general-purpose vision-language models is challenging due to the increased task discrepancy introduced by the additional visual input. Although vision-language pre-training has been widely studied, vision-language instruction tuning remains relatively less explored. In this paper, we conduct a systematic and comprehensive study on vision-language instruction tuning based on the pre-trained BLIP-2 models. We gather a wide variety of 26 publicly available datasets, transform them into instruction tuning format and categorize them into two clusters for held-in instruction tuning and held-out zero-shot evaluation. Additionally, we introduce instruction-aware visual feature extraction, a crucial method that enables the model to extract informative features tailored to the given instruction. The resulting InstructBLIP models achieve state-of-the-art zero-shot performance across all 13 held-out datasets, substantially outperforming BLIP-2 and the larger Flamingo. Our models also lead to state-of-the-art performance when finetuned on individual downstream tasks (e.g., 90.7% accuracy on ScienceQA IMG). Furthermore, we qualitatively demonstrate the advantages of InstructBLIP over concurrent multimodal models.*
Tips:
- InstructBLIP uses the same architecture as [BLIP-2](blip2) with a tiny but important difference: it also feeds the text prompt (instruction) to the Q-Former.
InstructBLIP architecture. Taken from the original paper.
This model was contributed by [nielsr](https://huggingface.co/nielsr).
The original code can be found [here](https://github.com/salesforce/LAVIS/tree/main/projects/instructblip).
## InstructBlipConfig
[[autodoc]] InstructBlipConfig
- from_vision_qformer_text_configs
## InstructBlipVisionConfig
[[autodoc]] InstructBlipVisionConfig
## InstructBlipQFormerConfig
[[autodoc]] InstructBlipQFormerConfig
## InstructBlipProcessor
[[autodoc]] InstructBlipProcessor
## InstructBlipVisionModel
[[autodoc]] InstructBlipVisionModel
- forward
## InstructBlipQFormerModel
[[autodoc]] InstructBlipQFormerModel
- forward
## InstructBlipForConditionalGeneration
[[autodoc]] InstructBlipForConditionalGeneration
- forward
- generate