-
FDU '25, UNC Exchange 23 Fall, UNC Research Intern
- Shanghai, China
- https://lillianwei-h.github.io
Highlights
- Pro
More
Stars
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 500+ LLMs (Qwen3, Qwen3-MoE, Llama4, InternLM3, DeepSeek-R1, ...) and 200+ MLLMs (Qwen2.5-VL, Qwen2.5-Omni, Qwen2-Audio, Ovis2, InternVL3, Llava, GLM4…
A comprehensive list of excellent research papers, models, datasets, and other resources on Vision-Language-Action (VLA) models in robotics.
A lightweight, powerful framework for multi-agent workflows
⚡ Dynamically generated stats for your github readmes
The official implementation of the paper "AgentSquare: Automatic LLM Agent Search in Modular Design Space""
MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Lillianwei-h / mmsg
Forked from leloykun/mmsgGenerate interleaved text and image content in a structured format you can directly pass to downstream APIs.
Lillianwei-h / runable-gill
Forked from kohjingyu/gillAdd inference code for json file and fix some bugs.
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
Let your Claude able to think
The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
[ICLR'25 Oral] MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models
💬 Create Dialogs, Visual Novels, RPGs, and manage Characters with Godot to create your Game!
1 min voice data can also be used to train a good TTS model! (few shot voice cloning)
Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.
🤯 Lobe Chat - an open-source, modern design AI chat framework. Supports multiple AI providers (OpenAI / Claude 4 / Gemini / DeepSeek / Ollama / Qwen), Knowledge Base (file upload / knowledge manage…
This template project is based on pytorch lightning and lightning-template. Please read the docs of them before using this template.
A generic project template lib based on pytorch lightning for project-template
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
A large model-based chatbot builder that can quickly integrate AI models (including ChatGPT, Claude, Gemini) into various software applications (such as Telegram, Gmail, Slack, and websites).
📖《网络代理与VPN应用详解》 详细阐述代理、隧道、VPN运作过程,并对GFW策略如:地址端口封锁、服务器缓存投毒、数字验证攻击、SSL连接阻断做相关的原理说明
Various translations of OSTEP can be found here. Help the cause and contribute!