We show for the first time that large-scale generative pretrained transformer (GPT) family
models can be pruned to at least 50% sparsity in one-shot, without any retraining, at minimal …

Generative Pre-trained Transformer models, known as GPT or OPT, set themselves apart
through breakthrough performance across complex language modelling tasks, but also by …

How to efficiently serve ever-larger trained natural language models in practice has become
exceptionally challenging even for powerful cloud servers due to their prohibitive …

This work studies post-training parameter quantization in large language models (LLMs).
We introduce quantization with incoherence processing (QuIP), a new method based on the …

Generative Pre-trained Transformer models, known as GPT or OPT, set themselves apart
through breakthrough performance across complex language modelling tasks, but also by …

Composing knowledge from multiple pieces of texts is a key challenge in multi-hop question
answering. We present a multi-hop reasoning dataset, Question Answering via Sentence …

We present MobileVLM, a competent multimodal vision language model (MMVLM) targeted
to run on mobile devices. It is an amalgamation of a myriad of architectural designs and …

We present ScienceWorld, a benchmark to test agents' scientific reasoning abilities in a new
interactive text environment at the level of a standard elementary school science curriculum …

Abstract Natural Language Inference (NLI) is fundamental to many Natural Language
Processing (NLP) applications including semantic search and question answering. The NLI …

A challenge in creating a dataset for machine reading comprehension (MRC) is to collect
questions that require a sophisticated understanding of language to answer beyond using …