Tag

LightRAG is an open-source framework designed for simple and fast Retrieval-Augmented Generation (RAG), integrating knowledge graphs, vector search, and efficient LLM-based processing to enhance question-answering over large document collections.

Open-source Python library from Hugging Face that supplies thousands of pretrained transformer models and utilities for text, vision, audio and multimodal tasks.

SGLang is a high-performance serving framework for large language models (LLMs) and vision-language models, designed for low-latency and high-throughput inference across single GPUs to large distributed clusters. Key features include RadixAttention for prefix caching, zero-overhead batch scheduling, prefill-decode disaggregation, speculative decoding, continuous batching, paged attention, tensor/pipeline/expert/data parallelism, structured outputs, chunked prefill, and quantization (FP4/FP8/INT4/AWQ/GPTQ). It supports a wide range of models like Llama, Qwen, DeepSeek, and hardware from NVIDIA, AMD, Intel, TPUs, with an intuitive frontend for LLM applications.

AI Toolkit is an all-in-one training suite for finetuning diffusion models, supporting image and video models on consumer-grade hardware. It offers GUI and CLI interfaces, making it user-friendly yet feature-rich, with capabilities for dataset handling, LoRA/LoKr training, layer-specific training, and integrations with platforms like RunPod and Modal. It supports models like FLUX.1 and SDXL, requiring an NVIDIA GPU with at least 24GB VRAM.

PyTorch Image Models (timm) is an open-source PyTorch library that aggregates a large collection of image model architectures, pretrained weights, training/validation/inference scripts, optimizers, schedulers and augmentations. It is widely used for research, reproducible ImageNet-style training, and as a convenient model/backbone provider for vision projects.

CleanRL is a high-quality, single-file implementation library for deep reinforcement learning (Deep RL). It provides compact, research-friendly standalone implementations of many RL algorithms (PPO, DQN, C51, DDPG, TD3, SAC, PPG, etc.), benchmarks, TensorBoard logging, Weights & Biases integration, and cloud/run tooling. It emphasizes readability, reproducibility, and ease of understanding rather than being a modular importable framework.

FunASR is an open-source end-to-end speech recognition toolkit (ASR) led by Alibaba DAMO Academy. It supports ASR, voice activity detection (VAD), punctuation restoration, speaker verification/diarization, multi-talker ASR, emotion recognition and more. FunASR provides many industrial-grade pretrained models, inference scripts, and deployment runtimes for research and production use.

LocalAI is a free, Open Source OpenAI alternative. It acts as a drop-in replacement REST API that's compatible with OpenAI API specifications for local AI inferencing. It allows you to run LLMs, generate images, audio, and more locally or on-prem with consumer-grade hardware, supporting multiple model families without requiring a GPU.

LLaVA is an open-source large language and vision assistant project that introduces visual instruction tuning to teach large language models to understand and follow multimodal (image+text) instructions. The repository includes papers, model checkpoints (Model Zoo), training and evaluation scripts, demos (Gradio), and tooling for fine-tuning, quantized inference, and deployment. LLaVA aims to bring LLM-level conversational capabilities to vision tasks and has continued evolving (LLaVA-1.5, LLaVA-NeXT, video/interactive variants).

garak is an open-source command-line LLM vulnerability scanner and red-teaming assessment kit. It probes large language models for failures such as hallucination, data leakage, prompt injection, misinformation, toxicity, jailbreaks, and other weaknesses. garak supports many backends (Hugging Face, OpenAI, Replicate, AWS Bedrock, gguf/llama.cpp, etc.), provides a wide range of probes and detectors, and produces structured logs and JSONL reports. Licensed under Apache-2.0.

A free 21-lesson course by Microsoft Cloud Advocates teaching beginners the fundamentals of building Generative AI applications. It covers concepts like Generative AI and LLMs, prompt engineering, chat apps, image generation, security, and more, with Python and TypeScript code samples supporting Azure OpenAI, OpenAI API, and open-source models. Features multi-language support, video intros, extra resources, and a Discord community.

An open-source repository from Stability AI that collects implementations, training configs, demos and inference scripts for multiple generative models (e.g. SDXL, SV3D, SV4D, SV4D 2.0, Stable Video Diffusion). It is modular and config-driven, provides sampling/demo scripts, training examples, and references to model weights on Hugging Face.