xiaoya-li

crewAI

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

spinningup

An educational resource to help anyone learn deep reinforcement learning.

langfun

OO for LLMs

llm.c

LLM training in simple, raw C/CUDA

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

anyskill

code for CVPR'24 "AnySkill: Learning Open-Vocabulary Physical Skill for Interactive Agents"

OpenDevin

🐚 OpenDevin: Code Less, Make More

gemma_pytorch

The official PyTorch implementation of Google's Gemma models

transformer-debugger

Inpaint-Anything

Inpaint anything using Segment Anything and inpainting models.

AnimatableGaussians

Code of [CVPR 2024] "Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling"

nanoGPT

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

GaussianObject

Code for "GaussianObject: Just Taking Four Images to Get A High-Quality 3D Object with Gaussian Splatting"

midGPT

Distributed pretraining of large language models (LLMs) on cloud TPU slices, with Jax and Equinox.

rembg

Rembg is a tool to remove images background

TripoSR

CommunityLM

[COLING 2022]: CommunityLM: Probing Partisan Worldviews from Language Models

ovsam

[arXiv preprint] The official code of paper "Open-Vocabulary SAM".

GaussianDreamer

GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models (CVPR 2024)

h2o-LLM-eval

Large-language Model Evaluation framework with Elo Leaderboard and A-B testing

objaverse-xl

🪐 Objaverse-XL is a Universe of 10M+ 3D Objects. Contains API Scripts for Downloading and Processing!

visual-spatial-reasoning

[TACL'23] VSR: A probing benchmark for spatial undersranding of vision-language models.

open-instruct

RL4LMs

A modular RL library to fine-tune language models to human preferences

LWM

text-to-video-synthesis-colab

Text To Video Synthesis Colab

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Awesome-Multimodal-Research

A curated list of Multimodal Related Research.

paws

This dataset contains 108,463 human-labeled and 656k noisily labeled pairs that feature the importance of modeling structure, context, and word order information for the problem of paraphrase identification.

InstantID

InstantID : Zero-shot Identity-Preserving Generation in Seconds 🔥