Stars
📦 Repomix is a powerful tool that packs your entire repository into a single, AI-friendly file. Perfect for when you need to feed your codebase to Large Language Models (LLMs) or other AI tools lik…
A curated list of research papers in Sentence Reprsentation Learning and a sts leaderboard of sentence embeddings.
Keeping language models honest by directly eliciting knowledge encoded in their activations.
Code for Cicero, an AI agent that plays the game of Diplomacy with open-domain natural language negotiation.
A modular RL library to fine-tune language models to human preferences
Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.
PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO
A clone of the card game Coup written in Node.js
A curated list of disentanglement in NLP. :-)
Faithfulness and factuality annotations of XSum summaries from our paper "On Faithfulness and Factuality in Abstractive Summarization" (https://www.aclweb.org/anthology/2020.acl-main.173.pdf).
PAIR.withgoogle.com and friend's work on interpretability methods
Simple image captioning model
[ICML 2021] Break-It-Fix-It: Unsupervised Learning for Program Repair
Chess reinforcement learning by AlphaGo Zero methods.
Mistral: A strong, northwesterly wind: Framework for transparent and accessible large-scale language model training, built with Hugging Face 🤗 Transformers.
Benchmarking Generalization to New Tasks from Natural Language Instructions
Must-read papers on prompt-based tuning for pre-trained language models.
Prefix-Tuning: Optimizing Continuous Prompts for Generation
TruthfulQA: Measuring How Models Imitate Human Falsehoods
A framework for analyzing computer vision models with simulated data
Backprop makes it simple to use, finetune, and deploy state-of-the-art ML models.
My take on a practical implementation of Linformer for Pytorch.
ImageNet-R(endition) and DeepAugment (ICCV 2021)
A Harder ImageNet Test Set (CVPR 2021)