yukang2017

lloco

The official repo for "LLoCo: Learning Long Contexts Offline"

ring-flash-attention

Ring attention implementation with flash attention

EasyContext

Memory optimization and training recipes to extrapolate language models' context length to 1 million tokens, with minimal hardware.

MiniGemini

Official implementation for Mini-Gemini

LSK3DNet

This is the official implementation of "LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels" (Accepted at CVPR 2024).

DeepCache

[CVPR 2024] DeepCache: Accelerating Diffusion Models for Free

grok-1

Grok open release

FollowYourClick

[arXiv 2024] Follow-Your-Click: This repo is the official implementation of "Follow-Your-Click: Open-domain Regional Image Animation via Short Prompts"

CUHK-PHD-Thesis-Template

CUHK PhD Thesis Template

notus

Notus is a collection of fine-tuned LLMs using SFT, DPO, SFT+DPO, and/or any other RLHF techniques, while always keeping a data-first approach

ChunkLlama

Data and code for our paper "Training-Free Long-Context Scaling of Large Language Models"

SPIN

The official implementation of Self-Play Fine-Tuning (SPIN)

Expert_Sparsity

LWM

Long-Context-Data-Engineering

Implementation of paper Data Engineering for Scaling Language Models to 128K Context

OLMo

Modeling, training, eval, and inference code for OLMo

AnyTool

VIRL

Code for V-IRL: Grounding Virtual Intelligence in Real Life

DDSM

Denoising Diffusion Step-aware Models (ICLR2024)

code-act

Official Repo for paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, Heng Ji.

TravelPlanner

Dataset and code for the paper "TravelPlanner: A Benchmark for Real-World Planning with Language Agents"

LongAlign

LongAlign: A Recipe for Long Context Alignment Encompassing Data, Training, and Evaluation

OpenMoE

A family of open-sourced Mixture-of-Experts (MoE) Large Language Models

AgentBoard

An Analytical Evaluation Board of Multi-turn LLM Agents

Medusa

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

parameter-efficient-moe

S-LoRA

S-LoRA: Serving Thousands of Concurrent LoRA Adapters

hydra-moe

ludwig

Low-code framework for building custom LLMs, neural networks, and other AI models

DeepSeek-MoE