RAG Foundry: A Framework for Enhancing LLMs for Retrieval Augmented Generation Paper • 2408.02545 • Published Aug 5 • 35
An Efficient Sparse Inference Software Accelerator for Transformer-based Language Models on CPUs Paper • 2306.16601 • Published Jun 28, 2023 • 4
Intel/distilbert-base-uncased-squadv1.1-sparse-80-1x4-block-pruneofa Question Answering • Updated Sep 20, 2022 • 19
Intel/bert-large-uncased-squadv1.1-sparse-80-1x4-block-pruneofa Question Answering • Updated Aug 1, 2022 • 27 • 1
Intel/bert-large-uncased-squadv1.1-sparse-90-unstructured Question Answering • Updated Dec 5, 2021 • 168
Intel/bert-base-uncased-mnli-sparse-70-unstructured-no-classifier Fill-Mask • Updated Jun 29, 2021 • 9