Highlights
- Pro
Lists (14)
Stars
Large-scale, Informative, and Diverse Multi-round Chat Data (and Models)
Holistic Evaluation of Language Models (HELM) is an open source Python framework created by the Center for Research on Foundation Models (CRFM) at Stanford for holistic, reproducible and transparen…
PPO x Family DRL Tutorial Course（决策智能入门级公开课：8节课帮你盘清算法理论，理顺代码逻辑，玩转决策AI应用实践 ）
A modular RL library to fine-tune language models to human preferences
🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch
800,000 step-level correctness labels on LLM solutions to MATH problems
Community for applying LLMs to robotics and a robot simulator with ChatGPT integration
Implementation of Toolformer, Language Models That Can Use Tools, by MetaAI
prompt2model - Generate Deployable Models from Natural Language Instructions
Code for ALBEF: a new vision-language pre-training method
Rigourous evaluation of LLM-synthesized code - NeurIPS 2023 & COLM 2024
Alpaca dataset from Stanford, cleaned and curated
Convert any music library into a music production sample-library with ML
solo-learn: a library of self-supervised methods for visual representation learning powered by Pytorch Lightning
AgentTuning: Enabling Generalized Agent Abilities for LLMs
Ongoing research training transformer language models at scale, including: BERT & GPT-2
An LLM-based autonomous agent controlling real-world applications via RESTful APIs
A large-scale text-to-image prompt gallery dataset based on Stable Diffusion
The implementation of "Prismer: A Vision-Language Model with Multi-Task Experts".
Train to 94% on CIFAR-10 in <6.3 seconds on a single A100. Or ~95.79% in ~110 seconds (or less!)
A tiny library for coding with large language models.
A generative and self-guided robotic agent that endlessly propose and master new skills.
Code for "Learning to summarize from human feedback"
VideoX: a collection of video cross-modal models
MultimodalC4 is a multimodal extension of c4 that interleaves millions of images with text.