facebookresearch / Sphere
Web-scale retrieval for knowledge-intensive NLP
☆552Updated last year
Related projects: ⓘ
- The AI Knowledge Editor☆181Updated 2 years ago
- Database Reasoning Over Text project for ACL paper☆353Updated 2 years ago
- Multi-angle c(q)uestion answering☆458Updated 2 years ago
- ☆362Updated last year
- Library for Knowledge Intensive Language Tasks☆905Updated 2 years ago
- ☆480Updated 7 months ago
- Used for adaptive human in the loop evaluation of language and embedding models.☆300Updated last year
- Task-based datasets, preprocessing, and evaluation for sequence models.☆552Updated this week
- Ask Me Anything language model prompting☆536Updated last year
- ☆1,100Updated last month
- Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled corpus and yields massive improvement: "GPL: …☆321Updated last year
- DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.☆163Updated 4 months ago
- Tools and Modeling Code for the MASSIVE dataset☆539Updated last year
- Adversarial Natural Language Inference Benchmark☆388Updated 2 years ago
- Mistral: A strong, northwesterly wind: Framework for transparent and accessible large-scale language model training, built with Hugging F…☆555Updated 10 months ago
- 🌸 fastText + Bloom embeddings for compact, full-coverage vectors with spaCy☆283Updated 10 months ago
- Prompt programming with FMs.☆437Updated last month
- Reproduce results and replicate training fo T0 (Multitask Prompted Training Enables Zero-Shot Task Generalization)☆456Updated last year
- Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch☆850Updated 10 months ago
- SpikeX - SpaCy Pipes for Knowledge Extraction☆397Updated 3 years ago
- Autoregressive Entity Retrieval☆756Updated last year
- Resources for the "SummEval: Re-evaluating Summarization Evaluation" paper☆361Updated 2 months ago
- A suite of tools for managing crowdsourcing tasks from the inception through to data packaging for research use.☆303Updated this week
- The pipeline for the OSCAR corpus☆161Updated 9 months ago
- We introduce MKQA, an open-domain question answering evaluation set comprising 10k question-answer pairs aligned across 26 typologically …☆162Updated 2 years ago
- Pipeline for pulling and processing online language model pretraining data from the web☆172Updated last year
- ToTTo is an open-domain English table-to-text dataset with over 120,000 training examples that proposes a controlled generation task: giv…☆434Updated last week
- Neural Search☆322Updated 3 months ago
- SummVis is an interactive visualization tool for text summarization.☆252Updated 2 years ago
- docTTTTTquery document expansion model☆350Updated last year