Yangjun Ruan

AI-Trader. "AI-Trader: 100% Fully-Automated Agent-Native Trading"

metaculus. TypeScript

forecasting-tools. A framework for building a AI Forecasting Bot for Metaculus. Additionally AI Forecasting tools to help humans forecast the future.

opencode. The open source coding agent.

SDPO. Reinforcement Learning via Self-Distillation (SDPO)

discover. Python

pepper. Python

harmony. Renderer for the harmony response format to be used with gpt-oss

nanotron. Minimalistic large language model 3D-parallelism training

picotron. Minimalistic 4D-parallelism distributed training framework for education purpose

codex. Lightweight coding agent that runs in your terminal

arxiv-latex-cleaner. arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

Math-Verify. Python

math-evaluation-harness. A simple toolkit for benchmarking LLMs on mathematical reasoning tasks. 🧮✨

blt. Code for BLT research paper

lingua. Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.

minbpe. Minimal, clean code for the Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization.

open_lm. A repository for research on medium sized language models.

dclm. DataComp for Language Models

public-tasks. HTML

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

scaling_laws_data_filtering. Python

research-career-tools. Python

OpenHands. 🙌 OpenHands: AI-Driven Development

mistral-inference. Official inference library for Mistral models

grok-1. Grok open release

LWM. Large World Model -- Modeling Text and Video with Millions Context

yet-another-applied-llm-benchmark. A benchmark to evaluate language models on questions I've previously asked them to solve.

litellm. Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]

OS-Copilot. An self-improving embodied conversational agent seamlessly integrated into the operating system to automate our daily tasks.

fastText. Library for fast text representation and classification.

code-act. Official Repo for ICML 2024 paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, Heng Ji.

VIRL. (ECCV 2024) Code for V-IRL: Grounding Virtual Intelligence in Real Life

bigcode-evaluation-harness. A framework for the evaluation of autoregressive code generation language models.

bigcode-dataset. Jupyter Notebook

sglang. SGLang is a high-performance serving framework for large language models and multimodal models.

autogen. A programming framework for agentic AI

Auto-GPT-Benchmarks. A repo built for the purpose of benchmarking the performance of agents, regardless of how they are set up and how they work.

openvibe. Modular Auto-GPT Framework

agents. An Open-source Framework for Data-centric, Self-evolving Autonomous Language Agents

llm-reasoners. A library for advanced large language model reasoning

SWE-bench. SWE-bench: Can Language Models Resolve Real-world Github Issues?

weak-to-strong. Python

datablations. Scaling Data-Constrained Language Models

webarena. Code repo for "WebArena: A Realistic Web Environment for Building Autonomous Agents"

PurpleLlama. Set of tools to assess and improve LLM security.

NexusRaven-V2. Jupyter Notebook

text-generation-inference. Large Language Model Text Generation Inference

XAgent. An Autonomous LLM Agent for Complex Task Solving

BestGPTs. Top ranked OpenAI GPTs

math-lm. Python

chain-of-thought-hub. Benchmarking large language models' complex reasoning ability with chain-of-thought prompting

WizardLM. LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath

lm-evaluation-harness. A framework for few-shot evaluation of language models.

LookaheadDecoding. [ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding

prm800k. 800,000 step-level correctness labels on LLM solutions to MATH problems

prompts.chat. f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

E2B. Open-source, secure environment with real-world tools for enterprise-grade agents.

awesome-ai-agents. A list of AI autonomous agents

promptmap. a security scanner for custom LLM applications

awesome-llm-security. A curation of awesome tools, documents and projects about LLM Security.

AgentGPT. 🤖 Assemble, configure, and deploy autonomous AI Agents in your browser.

letta. Platform for stateful agents: AI with advanced memory that can learn and self-improve over time.

openinterpreter. A lightweight coding agent for open models like Deepseek, Kimi, and Qwen

awesome-llm-powered-agent. Awesome things about LLM-powered agents. Papers / Repos / Blogs / ...

awesome-language-agents. List of language agents based on paper "Cognitive Architectures for Language Agents"

LLMAgentPapers. Must-read Papers on LLM Agents.

dspy. DSPy: The framework for programming—not prompting—language models

tree-of-thought-llm. [NeurIPS 2023] Tree of Thoughts: Deliberate Problem Solving with Large Language Models

natbot. Drive a browser with GPT-3

AgentBench. A Comprehensive Benchmark to Evaluate LLMs as Agents (ICLR'24)

openchat. OpenChat: Advancing Open-source Language Models with Imperfect Data

generative_agents. Generative Agents: Interactive Simulacra of Human Behavior

llm-attacks. Universal and Transferable Attacks on Aligned Language Models

llama. Inference code for Llama models

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

intercode. [NeurIPS 2023 D&B] Code repository for InterCode benchmark https://arxiv.org/abs/2306.14898

gpt-engineer. CLI platform to experiment with codegen. Precursor to: https://lovable.dev

TransformerPrograms. [NeurIPS 2023] Learning Transformer Programs

LLaMA-Adapter. [ICLR 2024] Fine-tuning LLaMA to follow Instructions within 1 Hour and 1.2M Parameters

open-instruct. AllenAI's post-training codebase

self-refine. LLMs can generate feedback on their work, use it to improve the output, and repeat this process iteratively.

ToolBench. [ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning.

Voyager. An Open-Ended Embodied Agent with Large Language Models

Gymnasium. A standard API for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

alpaca_farm. A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.

plugnplai. 🎸 Integrating AI plugins to LLMs

open_llama. OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset

twitter-agent. Build AI-powered Agents for Twitter🐣

lamini. The Official Python Client for Lamini's API

babyagi. Python

BMTools. Tool Learning for Big Models, Open-Source Solutions of ChatGPT-Plugins

toolkit-ai. AI-agents that automatically generate and use Langchain Tools and ChatGPT plugins

ChatArena. ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.

FastChat. An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

AutoGPT. AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

the-algorithm. Source code for the X Recommendation Algorithm

open_flamingo. An open-source framework for training large multimodal models.

dolly. Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform

ml_timeline.

self-instruct. Aligning pretrained language models with instruction data generated by themselves.

langchain. The agent engineering platform.

tuned-lens. Tools for understanding how transformer predictions are built layer-by-layer

codealpaca. Python

chatgpt-retrieval-plugin. The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.

evals. Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

stanford_alpaca. Code and documentation to train Stanford's Alpaca models, and generate the data.

openai-python. The official Python library for the OpenAI API

chain-of-hindsight. Simple next-token-prediction for RLHF

promptsource. Toolkit for creating, sharing and using natural language prompts.

HIR. Python

toolformer-pytorch. Implementation of Toolformer, Language Models That Can Use Tools, by MetaAI

sentiment_dataset. Python

few-shot-learning. Few-shot Learning of GPT-3

pet. This repository contains the code for "Exploiting Cloze Questions for Few-Shot Text Classification and Natural Language Inference"

openai-cookbook. Examples and guides for using the OpenAI API

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

PaLM-rlhf-pytorch. Implementation of RLHF (Reinforcement Learning with Human Feedback) on top of the PaLM architecture. Basically ChatGPT but with PaLM

evals.

ConstitutionalHarmlessnessPaper.

Prompt-Engineering-Guide. 🐙 Guides, papers, lessons, notebooks and resources for prompt engineering, context engineering, RAG, and AI Agents.

BIG-Bench-Hard. Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Them

scaling-laws-openclip. Reproducible scaling laws for contrastive language-image learning (https://arxiv.org/abs/2212.07143)

true_few_shot. Code for the paper "True Few-Shot Learning in Language Models" (https://arxiv.org/abs/2105.11447)

EditingClassifiers. Python

wise-ft. Robust fine-tuning of zero-shot models

influence-release. Jupyter Notebook

gpt-2. Code for the paper "Language Models are Unsupervised Multitask Learners"

ibot. iBOT :robot:: Image BERT Pre-Training with Online Tokenizer (ICLR 2022)

deep-vector-quantization. VQVAEs, GumbelSoftmaxes and friends

presentations. Python

GroupViT. Official PyTorch implementation of GroupViT: Semantic Segmentation Emerges from Text Supervision, CVPR 2022.

BIG-bench. Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models

Diffusion-LM. Diffusion-LM

tfrecord. Standalone TFRecord reader/writer with PyTorch data loaders

multi_object_datasets. Multi-object image datasets with ground-truth segmentation masks and generative factors.

vision_transformer. Jupyter Notebook

clrs. Jupyter Notebook

unilm. Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

vdm. Jupyter Notebook

imagen-pytorch. Implementation of Imagen, Google's Text-to-Image Neural Network, in Pytorch

continual-learning-baselines. Continual learning baselines and strategies from popular papers, using Avalanche. We include EWC, SI, GEM, AGEM, LwF, iCarl, GDumb, and other strategies.

DALL-E. PyTorch package for the discrete VAE used for DALL·E.

enhancing-transformers. An unofficial implementation of both ViT-VQGAN and RQ-VAE in Pytorch

taming-transformers. Taming Transformers for High-Resolution Image Synthesis

dalle-mini. DALL·E Mini - Generate images from a text prompt

slate. This is the official source code for SLATE. We provide the code for the model, the training code, and a dataset loader for the 3D Shapes dataset. This code is implemented in Pytorch.

metaseq. Repo for external large-scale work

asa. Code for paper "Adversarial Support Alignment"

Stylized-ImageNet. Code to create Stylized-ImageNet, a stylized version of standard ImageNet (ICLR 2019 Oral)

ffcv. FFCV: Fast Forward Computer Vision (and other ML workloads!)

mae. PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

DomainBed. DomainBed is a suite to test domain generalization algorithms

optdom. [ICLR'22] Self-supervised learning optimally robust representations for domain shift.

google-research. Google Research

vit-pytorch. Implementation of Vision Transformer, a simple way to achieve SOTA in vision classification with only a single transformer encoder, in Pytorch

moco. PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722

simclr. SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners

vissl. VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.

lightly. A python library for self-supervised learning on images.

DeCLIP. Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm

laion-prepro. Get hundred of million of image+url from the crawling at home dataset and preprocess them

clip-retrieval. Easily compute clip embeddings and build a clip retrieval system with them

pytorch-image-models. The largest collection of PyTorch image encoders / backbones. Including train, eval, inference, export scripts, and pretrained weights -- ResNet, ResNeXT, EfficientNet, NFNet, Vision Transformer (ViT), MobileNetV4, MobileNet-V3 & V2, RegNet, DPN, CSPNet, Swin Transformer, MaxViT, CoAtNet, ConvNeXt, and more

transferlearning. Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习

dino. PyTorch code for Vision Transformers training with the Self-Supervised learning method DINO

open_clip. An open source implementation of CLIP.

NeuralCompression. A collection of tools for neural compression enthusiasts.

MultiBench. [NeurIPS 2021] Multiscale Benchmarks for Multimodal Representation Learning

geotorch. Constrained optimization toolkit for PyTorch

vib_demo. Jupyter Notebook

imagenet-testbed. ImageNet Testbed, associated with the paper "Measuring Robustness to Natural Distribution Shifts in Image Classification."

SciencePlots. Matplotlib styles for scientific plotting

Beamer-template-uoft. Beamer template for University of Toronto

jonbarron.github.io. HTML

leonidk.github.io. a fork of https://jonbarron.info/ for use in jekyll builds with markdown page updates

al-folio. A beautiful, simple, clean, and responsive Jekyll theme for academics

minimal-light. A simple and elegant Jekyll theme for an academic personal homepage

cheat-sheets. Collection of cheat sheets for git, vim, shortcuts, linux commands, and so on.

latex-resources. Collection of LaTeX resources and examples.

BeamerStyleSlides. 🌈Beamer风格的幻灯片模板集。包含了PowerPoint和Keynote两套格式。

mtheme. A modern LaTeX Beamer theme

spectral-density. Hessian spectral density estimation in TF and Jax

deq-jax. [NeurIPS'19] Deep Equilibrium Models Jax Implementation

awesome-self-supervised-gnn. Papers about pretraining and self-supervised learning on Graph Neural Networks (GNN).

awesome-self-supervised-learning. A curated list of awesome self-supervised methods

CLIP. CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

awesome-domain-adaptation. A collection of AWESOME things about domain adaptation

Domain-generalization. All about domain generalization

InvariantRiskMinimization. PyTorch code to run synthetic experiments.

wilds. A machine learning benchmark of in-the-wild distribution shifts, with data loaders, evaluators, and default models.

diffusion. Denoising Diffusion Probabilistic Models

csc2541_examples. Python

hydra. Hydra is a framework for elegantly configuring complex applications

submitit. Python 3.8+ toolbox for submitting jobs to Slurm

VectorQuantizedVAE. A PyTorch implementation of "Continuous Relaxation Training of Discrete Latent Variable Image Models"

blackbox-backprop. Torch modules that wrap blackbox combinatorial solvers according to the method presented in "Differentiating Blackbox Combinatorial Solvers"

uncertainty-baselines. High-quality implementations of standard and SOTA methods on a variety of tasks.

BAM. Bayesian Attention Modules

improving-inference-for-neural-image-compression. Official code repo for NeurIPS 2020 paper "Improving Inference for Neural Image Compression"