SuperPrompt is an attempt to engineer prompts that might help us understand AI agents.

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑‍🔬

Run Effective Large Batch Contrastive Learning Beyond GPU/TPU Memory Constraint

A library of reinforcement learning components and agents

A command-line utility to download songs and playlists directly from Spotify's servers

Implementation of the paper: "Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention" from Google in pyTORCH

A natural language interface for computers

Make huge neural nets fit in memory

Build high-performance AI models with modular building blocks

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

Efficiently Fine-Tune 100+ LLMs in WebUI (ACL 2024)

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

PECOS - Prediction for Enormous and Correlated Spaces

A library for mechanistic interpretability of GPT-style language models

LLM Transparency Tool (LLM-TT), an open-source interactive toolkit for analyzing internal workings of Transformer-based language models. *Check out demo at* https://huggingface.co/spaces/facebook/l…

Collection of sbatch templates and examples for Arizona State University's Sol supercomputer.

A JAX research toolkit for building, editing, and visualizing neural networks.

A Native-PyTorch Library for LLM Fine-tuning

Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.

Open weights language model from Google DeepMind, based on Griffin.

Dermatology ddx dataset, Jax implementations of Monte Carlo conformal prediction, plausibility regions and statistical annotation aggregation from our recent work on uncertain ground truth (TMLR'23…

Zotero is a free, easy-to-use tool to help you collect, organize, annotate, cite, and share your research sources.

Accelerated vector search using RAPIDS cuVS.

JORA: JAX Tensor-Parallel LoRA Library (ACL 2024)

JAX implementation of the Llama 2 model

Implementation of https://srush.github.io/annotated-s4

⏰ AI conference deadline countdowns

A minimal pytorch package implementing a gradient reversal layer.

Repository for "Detoxification with MaRCo: Controllable Revision with Experts and Anti-Experts"