evelynmitchell Goto Github PK

alignment-handbook

Robust recipes for Alignment

alignprop

AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more sample and compute efficient than reinforcement learning methods (PPO) for finetuning Stable Diffusion

alloy_models

A public repository to host Alloy models. This repository holds public models to be used as entertainment, examples, tutorials, utilities, and proofs.

alpaca-lora

Instruct-tune LLaMA on consumer hardware

alphacodium

alphafold

Open source code for AlphaFold.

alphageometry

alternat

High availability implementation of AWS NAT instances.

annotated-s4

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

annotated_deep_learning_paper_implementations

🧑‍🏫 59 Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

anthropic-sdk-python

anythingbutwrappers

ao

The torchao repository contains api's and workflows for quantization and pruning gpu models.

aos-dr

This cFS app is called Diagnostic Reasoner (DR), and as the name implies, it will diagnose a system of interest. That is, it will do fault detection and fault isolation. A more complete description of DR and how it works can be found in the DR User's Manual, in the doc dir.

approaching-an-unknown-communication-system

Code/supplement for the paper "Approaching an unknown communication system by latent space exploration and causal inference"

aprl

Efficient Real-World RL for Legged Locomotion via Adaptive Policy Regularization

aqlm

Official Pytorch repository for Extreme Compression of Large Language Models via Additive Quantization https://arxiv.org/pdf/2401.06118.pdf

arc-agi

The Abstraction and Reasoning Corpus

archai

Accelerate your Neural Architecture Search (NAS) through fast, reproducible and modular research.

archer

Research Code for "ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL"

arithmetic

Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (2024)

arxivpapers

Code behind Arxiv Papers

assemblyphysics

ast_t5

async_python_testing_tutorial

atomate

atomate is a powerful software for computational materials science and contains pre-built workflows.

attention-is-all-you-need-pytorch

A PyTorch implementation of the Transformer model in "Attention is All You Need".

attention_head_varieties

attention_with_linear_biases

Code for the ALiBi method for transformer language models (ICLR 2022)

audioseal

Localized watermarking for AI-generated speech audios, with SOTA on robustness and very fast detector