Building reliable software from natural language prompts remains a major challenge—even for today’s most capable large language models (LLMs). While…
LlamaFactory: Fine-Tune 100+ Language Models Effortlessly—No Coding Required 63856
Fine-tuning large language models (LLMs) used to be a complex, time-consuming endeavor—requiring deep expertise in deep learning frameworks, custom code…
llama.cpp: Run Large Language Models Anywhere—Fast, Lightweight, and Offline 91182
In an era where large language models (LLMs) power everything from chatbots to code assistants, deploying them outside of cloud…
BitNet: Run 1.58-Bit LLMs Locally on CPUs with 6x Speedup and 82% Less Energy 24452
Running large language models (LLMs) used to require powerful GPUs, expensive cloud infrastructure, or specialized hardware—until BitNet changed the game.…
WebLLM: Run Large Language Models Entirely in the Browser—No Server, No Cloud, Full Privacy 16945
Imagine running powerful large language models (LLMs)—like Llama 3, Mistral, or Phi 3—directly inside a user’s web browser, with no…
TradingAgents: A Multi-Agent LLM Framework That Mirrors Real Trading Desks for Smarter Financial Decisions 26486
Automated financial trading has long relied on rule-based systems or single-agent machine learning models that struggle to capture the nuanced,…
Verl: A Flexible, High-Performance RLHF Framework for Aligning Large Language Models at Scale 17406
Verl (short for Volcano Engine Reinforcement Learning) is an open-source, production-ready framework designed specifically for Reinforcement Learning from Human Feedback…
Open-Sora: Build Commercial-Quality AI Videos for $200K — Fully Open-Source and Production-Ready 28098
Open-Sora is a groundbreaking open-source initiative that makes high-quality AI video generation accessible, efficient, and affordable. With the release of…
Paper2Code: Automatically Turn Machine Learning Research Papers into Ready-to-Run Code Repositories 3875
Reproducing results from machine learning (ML) research papers is often a frustrating experience. Despite the surge in published work, a…
R&D-Agent: Automate End-to-End AI Development with a Dual-Agent Framework That Tops MLE-Bench 9745
Building high-performing, data-driven AI solutions remains a labor-intensive, iterative process—even for seasoned machine learning engineers. From brainstorming novel modeling ideas…