A curated list of Large Language Model (LLM) Interpretability resources.Awesome LLM Interpretability A curated list of amazingly awesome tools, papers, articles, and communities focused on Large Language Model (LLM) Interpretability. Table of Contents Awesome LLM Interpretability LLM Interpretability Tools LLM Interpretability Papers LLM Interpretability Articles LLM Interpretability Groups LLM Interpretability Tools Tools and libraries for LLM interpretability and analysis. Comgra - Com…
📜 A minimalist personal website embodying the purity of paper and freshness of snow.Shiro 一个极简主义的个人网站，体现了纸的纯净和雪的清新。 为 Mix Space 服务的个人站点前端。 以下是一些使用 Shiro 的示例站点： 静かな森 可愛い松 HuaSui 天翔 TNXG Star 欢迎你来体验 Shiro 的魅力！ ✨ 特征 🚀 SEO 100%，性能优秀：在 LightHouse 中表现优秀，Performance > 90%，Best practice > 90%。 🎨 UI 现代化，简洁不简单：用户界面设计现代化，简洁而不简单，让你的体验更加流畅。 💎 注重细节，UX 极致：注重每一个细节，所有的动画都使用符合物理的 Spring 弹性动画，每一帧都是大自然的感觉。 🔔 接入 WebSocket，实时获取最新的文章通知：通过 WebSocket，访客能够实时获取最新的文章通知。 💻 实时活动状态展示：配合 ProcessReporter，可以在主页上显示实时活动…
A unified evaluation framework for large language models PromptBench: A Unified Library for Evaluating and Understanding Large Language Models. Paper · Documentation · Leaderboard · More papers Table of Contents News and Updates Introduction Installation Usage Datasets and Models Benchmark Results Acknowledgments News and Updates [16/12/2023] Add support for Gemini, Mistral, Mixtral, B…
GUI-focused roop Rope implements the insightface inswapper_128 model with a helpful GUI. Discord Donate Wiki Demo Video ${{\color{Goldenrod}{\textsf{Last Updated 2023-12-25 08:56 PST}}}}$ note: you need to download the latest GFPGAN model for Ruby. Link is in the wiki Features: Lightning speed face swapping with all the features Upscalers Likeness modifiers Orientation management Masks: borders, differentials, auto occlusion, face parsers, text-based masking - all with strength adjustments a…
Community designed ERCF v2Enraged Rabbit Community Project ERCF v2 - RC1 An expandable MMU for Klipper based 3D-Printers This is a community born project and major update to the Voron ERCF MMU that was started a couple of years ago by Ette. It is endorsed by Ette and the guiding philosophy wasn't to start again with a new MMU design but to refine what has already proven to be a very capable machine and push it to be the best it can be by simplifying prob…
Ferret: Refer and Ground Anything Anywhere at Any Granularity An End-to-End MLLM that Accept Any-Form Referring and Ground Anything in Response. [Paper] Haoxuan You*, Haotian Zhang*, Zhe Gan, Xianzhi Du, Bowen Zhang, Zirui Wang, Liangliang Cao, Shih-Fu Chang, Yinfei Yang [*: equal contribution] Overview Diagram of Ferret Model. Key Contributions: Ferret Model - Hybrid Region Representation + Spatial-aware Visual Sampler enable fine-grained and open-vocabulary referring and ground…
A dedicated scratchpad for developersHeynote Heynote is a dedicated scratchpad for developers. It functions as a large persistent text buffer where you can write down anything you like. Works great for that Slack message you don't want to accidentally send, a JSON response from an API you're working with, notes from a meeting, your daily to-do list, etc. The Heynote buffer is divided into blocks, and each block can have its own Language set (e.g. JavaScript, JSON, Markdown, etc.). This…
A novel LLM-based multimodal agent framework designed to operate smartphone applicationsAppAgent Chi Zhang*, Zhao Yang*, Jiaxuan Liu*, Yucheng Han, Xin Chen, Zebiao Huang, Bin Fu, Gang Yu (Corresponding Author) (* equal contributions) 🔆 Introduction We introduce a novel LLM-based multimodal agent framework designed to operate smartphone applications. Our framework enables the agent to operate smartphone applications through a simplified action space, mimicking human…
🏆 Welcome to TON Smart Challenge #5 by TON Foundation & Codeforces 📝 Tasks Inheritance Smart Contract Splitter Smart Contract Universal Versioning Template Quantum Maze The goal of the contestants is to provide a code that matches the description. Each task except Task 4 may give the contestant either 0 or 5 to 6 score points: 5 for all tests passed plus "gas-score" from 0 to 1 (0 for "infinite" gas consumption, 1 for 0 gas consumption, dependence is inverse exponent). Tas…