facebookresearch / Sphere
Web-scale retrieval for knowledge-intensive NLP
☆552Updated 2 years ago
Alternatives and similar repositories for Sphere:
Users that are interested in Sphere are comparing it to the libraries listed below
- The AI Knowledge Editor☆183Updated 2 years ago
- 🌸 fastText + Bloom embeddings for compact, full-coverage vectors with spaCy☆309Updated last year
- Used for adaptive human in the loop evaluation of language and embedding models.☆306Updated 2 years ago
- Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled corpus and yields massive improvement: "GPL: …☆330Updated last year
- Search Engines with Autoregressive Language models☆282Updated last year
- Library for Knowledge Intensive Language Tasks☆933Updated 2 years ago
- Ask Me Anything language model prompting☆545Updated last year
- Database Reasoning Over Text project for ACL paper☆354Updated 2 years ago
- ☆362Updated 3 months ago
- ☆182Updated last year
- Reproduce results and replicate training fo T0 (Multitask Prompted Training Enables Zero-Shot Task Generalization)☆463Updated 2 years ago
- Neural Search☆327Updated 9 months ago
- SpikeX - SpaCy Pipes for Knowledge Extraction☆397Updated 3 years ago
- We introduce MKQA, an open-domain question answering evaluation set comprising 10k question-answer pairs aligned across 26 typologically …☆173Updated 2 years ago
- A library to synthesize text datasets using Large Language Models (LLM)☆151Updated 2 years ago
- DeepSpeed is a deep learning optimization library that makes distributed training easy, efficient, and effective.☆164Updated this week
- A Python framework for performing information retrieval experiments, building on http://terrier.org/☆438Updated last week
- docTTTTTquery document expansion model☆361Updated last year
- A suite of tools for managing crowdsourcing tasks from the inception through to data packaging for research use.☆309Updated 3 months ago
- Adversarial Natural Language Inference Benchmark☆394Updated 2 years ago
- Code and data to support the paper "PAQ 65 Million Probably-Asked Questions andWhat You Can Do With Them"☆202Updated 3 years ago
- ToTTo is an open-domain English table-to-text dataset with over 120,000 training examples that proposes a controlled generation task: giv…☆441Updated 6 months ago
- Find and fix bugs in natural language machine learning models using adaptive testing.☆182Updated 10 months ago
- ✨ Bootstrap annotation with zero- & few-shot learning via OpenAI GPT-3☆322Updated last year
- Zero and Few shot named entity & relationships recognition☆360Updated 3 months ago
- OpenAlpaca: A Fully Open-Source Instruction-Following Model Based On OpenLLaMA☆301Updated last year
- Comprehensive NLP Evaluation System☆186Updated 7 months ago
- Implementation of RETRO, Deepmind's Retrieval based Attention net, in Pytorch☆858Updated last year
- SGPT: GPT Sentence Embeddings for Semantic Search☆864Updated last year
- Mistral: A strong, northwesterly wind: Framework for transparent and accessible large-scale language model training, built with Hugging F…☆569Updated last year