hxixixh

longhorn_cuda

CUDA kernels for the Longhorn Architecture

edm

Elucidating the Design Space of Diffusion-Based Generative Models (EDM)

rfpp

The codebase of our paper "Improving the Training of Rectified Flows"

AdaFlow

Official PyTorch implementation of AdaFlow

DynMM

Code for the paper 'Dynamic Multimodal Fusion'

MFH

[ICLR 23 oral] The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation

AlignEgoExo

Code and data release for the paper "Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignment" (NeurIPS 2023)

EgoT2

Code release for the paper "Egocentric Video Task Translation" (CVPR 2023 Highlight)

VidOSC

Code and data release for the paper "Learning Object State Changes in Videos: An Open-World Perspective" (CVPR 2024)

nanoGPT

The simplest, fastest repository for training/finetuning medium-sized GPTs.

ZO-LLM

[ICML 2024] Official code for the paper "Revisiting Zeroth-Order Optimization for Memory-Efficient LLM Fine-Tuning: A Benchmark ".

MeZO

[NeurIPS 2023] MeZO: Fine-Tuning Language Models with Just Forward Passes. https://arxiv.org/abs/2305.17333

styleguide

Style guides for Google-originated open-source projects

asyncdiloco

LaViLa

Code release for "Learning Video Representations from Large Language Models"

consistency_models_toy_task

Unofficial minimal implementation of consistency models (CM) proposed by Song et al. 2023 on a 1D toy task in pytorch

AVION

Code release for "Training a Large Video Model on a Single Machine in a Day"

consistency_models

Official repo for consistency models.

mamba

Mamba SSM architecture

llama-recipes

Scripts for fine-tuning Meta Llama3 with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama3 for WhatsApp & Messenger.

llama

Inference code for Llama models

stable-diffusion

A latent text-to-image diffusion model

llama_index

LlamaIndex is a data framework for your LLM applications

transformer

Transformer: PyTorch Implementation of "Attention Is All You Need"

InstaFlow

:zap: InstaFlow! One-Step Stable Diffusion with Rectified Flow (ICLR 2024)

awesome-chatgpt-prompts

This repo includes ChatGPT prompt curation to use ChatGPT better.

metric-residual-network

Official PyTorch Implementation for Metric Residual Networks for Sample Efficient Goal-Conditioned Reinforcement Learning

CAGrad

Official PyTorch Implementation for Conflict-Averse Gradient Descent (CAGrad)

llm-pddl

RectifiedFlow

Official Implementation of Rectified Flow (ICLR2023 Spotlight)