Graphcore / lxmert-base-ipu

Graphcore/lxmert-base-ipu

Optimum Graphcore is a new open-source library and toolkit that enables developers to access IPU-optimized models certified by Hugging Face. It is an extension of Transformers, providing a set of performance optimization tools enabling maximum efficiency to train and run models on Graphcore’s IPUs - a completely new kind of massively parallel processor to accelerate machine intelligence. Learn more about how to take train Transformer models faster with IPUs at hf.co/hardware/graphcore .

Through HuggingFace Optimum, Graphcore released ready-to-use IPU-trained model checkpoints and IPU configuration files to make it easy to train models with maximum efficiency in the IPU. Optimum shortens the development lifecycle of your AI models by letting you plug-and-play any public dataset and allows a seamless integration to our State-of-the-art hardware giving you a quicker time-to-value for your AI project.

Model description

LXMERT is a transformer model for learning vision-and-language cross-modality representations. It has a Transformer model that has three encoders: object relationship encoder, a language encoder, and a cross-modality encoder. It is pretrained via a combination of masked language modelling, visual-language text alignment, ROI-feature regression, masked visual-attribute modelling, masked visual-object modelling, and visual-question answering objectives. It achieves the state-of-the-art results on VQA and GQA.

Paper link : LXMERT: Learning Cross-Modality Encoder Representations from Transformers

Intended uses & limitations

This model contains just the IPUConfig files for running the lxmert-base-uncased model on Graphcore IPUs.

This model contains no model weights, only an IPUConfig.

Usage

from optimum.graphcore import IPUConfig
ipu_config = IPUConfig.from_pretrained("Graphcore/lxmert-base-ipu")