JEEBench, EMNLP 2023

A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.

MTEB: Massive Text Embedding Benchmark

LLM inference in C/C++

A high-throughput and memory-efficient inference and serving engine for LLMs

Multilingual Sentence & Image Embeddings with BERT

Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'

Devika is an Agentic AI Software Engineer that can understand high-level human instructions, break them down into steps, research relevant information, and write code to achieve the given objective…

Generative Representational Instruction Tuning

Finetune Llama 3.1, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory

RAG for any docs hosted on readthedocs

Modeling, training, eval, and inference code for OLMo

Integrating Paperpile with Notion Databases 🔄

Go app that allows you to access your reMarkable tablet files through the Cloud API

A script for synchronizing the reMarkable e-reader

Fetch an academic paper or web article and send it to the reMarkable tablet with a single command

A curated list of projects related to the reMarkable tablet

additional functionality via binary patching

remarkable2 framebuffer reversing

GPT4 based personalized ArXiv paper assistant bot

Examples and guides for using the OpenAI API

[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings

This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.

[ICLR 2024] Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821

ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)

Code and Data for "Evaluating Correctness and Faithfulness of Instruction-Following Models for Question Answering"

DSPy: The framework for programming—not prompting—foundation models

ACL 2023: Evaluating Open-Domain Question Answering in the Era of Large Language Models

Pretraining Efficiently on S2ORC!