timhartill
Follow
Stars
Question and Answer based on Anything.
Automatically create Faiss knn indices with the most optimal similarity search parameters.
S2ORC: The Semantic Scholar Open Research Corpus: https://www.aclweb.org/anthology/2020.acl-main.447/
PyTorch code and models for V-JEPA self-supervised learning from video.
Contriever: Unsupervised Dense Information Retrieval with Contrastive Learning
🦜🔗 Build context-aware reasoning applications
TruthfulQA: Measuring How Models Imitate Human Falsehoods
StableLM: Stability AI Language Models
Code and documentation to train Stanford's Alpaca models, and generate the data.
Trained models & code to predict toxic comments on all 3 Jigsaw Toxic Comment Challenges. Built using ⚡ Pytorch Lightning and 🤗 Transformers. For access to our API, please email us at contact@unita…
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
A collection of libraries to optimise AI model performances
Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM
Various utility scripts useful for natural language processing, machine translation, etc.
Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models
The official code of TACL 2022, "Break, Perturb, Build: Automatic Perturbation of Reasoning Paths Through Question Decomposition".
A large annotated semantic parsing corpus for developing natural language interfaces.
Data and Code Release for "On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queries"
Training T5 to perform numerical reasoning.
Dataset and code for “Going on a vacation” takes longer than “Going for a walk”: A Study of Temporal Commonsense Understanding, EMNLP 2019.
Implementation of the paper: "Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skills"
Repository for Teaching Broad Reasoning Skills for Multi-Step QA by Generating Hard Contexts, EMNLP22
A web application for playing 20 Questions to crowdsource common sense. 🤖