roberta-large-ipu / README.md
internetoftim's picture
Update README.md
7691ac8

Graphcore/roberta-large-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

RoBERTa is based on BERT pretraining approach and improves on it by carefully evaluating a number of design decisions of BERT pretraining which it found to cause the model to be undertrained.

It suggested a way to improve the performance by training the model longer, with bigger batches over more data, removing the next sentence prediction objectives, training on longer sequences and dynamically changing the mask pattern applied to the training data.

As a result, it achieved state-of-the-art results on GLUE, RACE and SQuAD.

Paper link : RoBERTa: A Robustly Optimized BERT Pretraining Approach

Intended uses & limitations

This model contains just the IPUConfig files for running the roberta-large 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/roberta-large-ipu")