A modular Python toolkit developed by the University of Innsbruck that integrates information retrieval, re-ranking, and RAG generation, featuring 40+ pre-processed datasets and single-line pipeline construction.
Official code repository for the O'Reilly book "Hands-On Large Language Models". Features 12 core chapters and bonus content covering Tokens, Transformers, RAG, and Fine-tuning. Includes 300+ illustrations and runnable Jupyter Notebooks optimized for Colab and local environments.
A comprehensive AI engineering hub featuring 93+ production-ready projects with in-depth tutorials and implementations for LLMs, RAGs, AI Agents, and MCP, covering beginner to advanced skill levels.
An end-to-side omnimodal LLM by Tsinghua THUNLP supporting vision, speech, and full-duplex multimodal live streaming, optimized for mobile deployment with performance rivaling Gemini 2.5 Flash.
Fully automatic censorship removal tool for language models using directional ablation with TPE parameter optimization to remove safety alignment while minimizing refusal behaviors and preserving original model capabilities. Supports dense, multimodal, and MoE architectures.
An open-sourced end-to-end VLM-based GUI Agent developed by Tsinghua University and Zhipu AI, built on GLM-4V-9B bilingual VLM, enabling cross-platform GUI automation and reasoning via screenshots and natural language instructions.
A curated collection of resources for Long Chain-of-Thought (Long-CoT) reasoning in LLMs, featuring papers, implementations, and datasets to track the latest advancements in the field.
An agentic graph language assistant framework developed by HKUDS, based on Llama3-8B, unifying predictive tasks (e.g., node classification) and generative tasks (e.g., text summarization) on graph data through collaborative agents for generation, planning, and execution.
Fast and accurate automatic speech recognition (ASR) optimized for edge devices. Features streaming support, voice intent recognition, and speaker identification with significantly lower latency than Whisper (107ms on Mac with Medium model). Provides unified API across iOS, Android, Linux, Windows, and macOS, ideal for robotics, smart home, and IoT applications.
An LLM post-training framework for RL scaling by Tsinghua THUDM, deeply integrating Megatron-LM training with SGLang inference engine for distributed reinforcement learning on large models like GLM, Qwen, DeepSeek, and Llama.
Page 1 / 5 · 43 total
Get the latest AI tools and trends delivered straight to your inbox. No spam, just intelligence.
