Train and evaluate embeddings for similarity search with PyTorch. Includes contrastive losses, hard example mining, samplers, and retrieval metrics.
- metric-learning
- deep-learning
- computer-vision
- machine-learning
97,836 visible repositories in the index
73–96 of 501 · Most stars
Train and evaluate embeddings for similarity search with PyTorch. Includes contrastive losses, hard example mining, samplers, and retrieval metrics.
Rules engine for cloud security, cost optimization, and governance, DSL in yaml for policies to query, filter, and take actions on resources
Semi-automated research assistant for academic research and software development. Supports Claude Code, Codex CLI, Kimi Code CLI, and OpenCode across ideation, coding, experiments, writing, and publication.
⚒ Evolutionary self-improvement for Hermes Agent — optimize skills, prompts, and code using DSPy + GEPA
A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM, TensorRT, vLLM, etc. to optimize inference speed.
A hardware-agnostic SDK for optimization problems: define a problem once, then lower it to any quantum or classical solver
High-performance TensorFlow library for quantitative finance.
FastF1 is a python package for accessing and analyzing Formula 1 results, schedules, timing data and telemetry
Build, Evaluate, and Optimize AI Systems. Includes evals, RAG, agents, fine-tuning, synthetic data generation, dataset management, MCP, and more.
A Next-Generation Training Engine Built for Ultra-Large MoE Models
VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models
Silky smooth profiling for Django
Tiled Diffusion and VAE optimize, licensed under CC BY-NC-SA 4.0
Translatedtext2vec, text to vector. A text vector representation tool that converts text into vector matrices. It implements text representation and text similarity calculation models such as Word2Vec, RankBM25, Sentence-BERT, and CoSENT, and works out of the box.
MlFinLab helps portfolio managers and traders who want to leverage the power of machine learning by providing reproducible, interpretable, and easy to use tools.
An AI Gateway, registry, and proxy that sits in front of any MCP, A2A, or REST/gRPC APIs, exposing a unified endpoint with centralized discovery, guardrails and management. Optimizes Agent & Tool calling, and supports plugins.
🦛 CHONK docs with Chonkie ✨ — The lightweight ingestion library for fast, efficient and robust RAG pipelines
Switch between multiple Claude Code accounts, with automatic rate-limit rotation, usage dashboard, and parallel sessions
Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation
[CVPR 2025] EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation
TranslatedAI Vtuber is a virtual streamer [Live2D/UE/xuniren] powered by [ChatterBot/ChatGPT/claude/langchain/chatglm/text-gen-webui/闻达 (Wenda)/千问 (Qianwen)/kimi/ollama]. It can interact with viewers in real time in live streams on [Bilibili/抖音 (Douyin)/快手 (Kuaishou)/微信视频号 (WeChat Channels)/拼多多 (Pinduoduo)/斗鱼 (Douyu)/YouTube/twitch/TikTok], or chat directly on the local machine. It uses TTS technology [edge-tts/VITS/elevenlabs/bark/bert-vits2/睿声 (Ruisheng)] to generate replies and can optionally change the voice with [so-vits-svc/DDSP-SVC]; commands work together with SD to draw images.
TranslatedSearch all Chinese NLP datasets, with commonly used English NLP datasets included
Bazarr is a companion application to Sonarr and Radarr. It manages and downloads subtitles based on your requirements. You define your preferences by TV show or movie and Bazarr takes care of everything for you.
LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence https://arxiv.org/abs/2609.17488