Expert Specialized Fine-TuningExpert-Specialized Fine-Tuning Official Repo for paper Let the Expert Stick to His Last: Expert-Specialized Fine-Tuning for Sparse Architectural Large Language Models by Zihan Wang, Deli Chen, Damai Dai, Runxin Xu, Zhuoshu Li and Y. Wu. ESFT aims to efficiently customize Large Language Models (LLMs) with Mixture-of-Experts (MoE) architecture by adjusting only task-relevant parts, improving efficiency and performance while using fewer resources and storage. 📰 News 📅…
Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.Qwen2.5-VL 💜 Qwen Chat | 🤗 Hugging Face | 🤖 ModelScope | 📑 Blog | 📚 Cookbooks | 📑Paper(is coming) 🖥️ Demo | 💬 WeChat (微信) | 🫨 Discord | 📑 API | 🖥️ PAI-DSW Introduction In the past five months since Qwen2-VL's release, numerous developers have built new models on the Qwen2-VL vision-language models, providing us with valuabl…
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models Model Download | Evaluation Results | Quick Start | License | Citation Paper Link👁️ 1. Introduction DeepSeekMath is initialized with DeepSeek-Coder-v1.5 7B and continues pre-training on math-related tokens sourced from Common Crawl, together with natural language and code data for 500B tokens…
Janus-Series: Unified Multimodal Understanding and Generation Models 🚀 Janus-Series: Unified Multimodal Understanding and Generation Models 📥 Model Download | ⚡ Quick Start | 📜 License | 📖 Citation 🤗 Online Demo (Janus-Pro-7B, Janus, JanusFlow) News 2025.01.27: Janus-Pro is released, an advanced version of Janus, improving both multimodal understanding and visual generation significantly. See paper 2024.11.1…
The open source Cursor for Designers. Design directly in your live React app and publish your changes to code. Onlook Cursor for Designers Explore the docs » View Demo · Report Bug · Request Feature Table of Contents Installation Usage Roadmap Contributing Contact Acknowledgments License The open-source Cursor for Designers Seamlessly integrate with any website or web app running on React + Tailw…
Compile shell scripts to static binaries. Bunster Have you ever wished your shell scripts could be faster, more portable, and secure ? Bunster brings this to life by transforming your shell scripts into efficient, standalone binaries that are easy to distribute and deploy across platforms (only unix is supported at the moment). Unlike other tools, Bunster doesn’t just wrap your scripts in a binary—it compiles them down to efficient native machine code, leveraging the powerful Go toolc…
Lightpanda: the headless browser designed for AI and automation Lightpanda Browser lightpanda.io Lightpanda is the open-source browser made for headless usage: Javascript execution Support of Web APIs (partial, WIP) Compatible with Playwright, Puppeteer through CDP (WIP) Fast web automation for AI agents, LLM training, scraping and testing with minimal memory footprint: Ultra-low memory footprint (9x less than Chrome) Exceptionally fast execution (11x faster than Chrome) & inst…
AI Engineering Hub 🚀 Welcome to the AI Engineering Hub! 🌟 Why This Repo? AI Engineering is advancing rapidly, and staying at the forefront requires both deep understanding and hands-on experience. Here, you will find: In-depth tutorials on LLMs and RAGs Real-world AI agent applications Examples to implement, adapt, and scale in your projects Whether you’re a beginner, practitioner, or researcher, this repo provides resources for all skill levels to experiment and succeed in AI engineering. 📬…
Get started quickly with Next.js, Postgres, Stripe, and shadcn/ui.Next.js SaaS Starter This is a starter template for building a SaaS application using Next.js with support for authentication, Stripe integration for payments, and a dashboard for logged-in users. Demo: https://next-saas-start.vercel.app/ Features Marketing landing page (/) with animated Terminal element Pricing page (/pricing) which connects to Stripe Checkout Dashboard pages with CRUD operations on users/teams Basic RBAC with …