Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

🌟 The Multi-Agent Framework: First AI Software Company, Towards Natural Language Programming

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

"🐈 nanobot: The Ultra-Lightweight Personal AI Agent"

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

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

ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型

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

s1: Simple test-time scaling

Repair malformed JSON from LLMs, APIs, logs, and user input in Python.

Universal and Transferable Attacks on Aligned Language Models

[ICCV 2023] Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation

Set of tools to assess and improve LLM security.

基于ChatGLM-6B + LoRA的Fintune方案

Fine-tuning ChatGLM-6B with PEFT | 基于 PEFT 的高效 ChatGLM 微调

Security scanner for AI agents, MCP servers and agent skills.

SAM: Sharpness-Aware Minimization (PyTorch)

A basic user tool to execute simple docker containers in batch or interactive systems without root privileges.

[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

A curated list of Multimodal Related Research.

Latest Advances on System-2 Reasoning

MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversation

Dialogue model that produces empathetic responses when trained on the EmpatheticDialogues dataset.

A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.

[NeurIPS 2022] 🛒WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents

Multi-modality pre-training

t-SNE experiments in pytorch

[SIGIR 2024 perspective] The implementation of paper "On Generative Agents in Recommendation"