Havuz

AuK, tek bir doğal dil talimat arayüzüyle konuşma üretimi ve düzenleme görevlerini gerçekleştiren açık ağırlıklı bir speech modelidir.

Neden yükseliyor · Yeni yayımlanmış bir model olarak kısa sürede 1308 yıldız almış; son 28 gündeki 30 commit ve 5 farklı yazar da aktif geliştirmeye işaret ediyor. README ayrıca vLLM-Omni, SGLang-Omni ve audio.cpp desteğini, modelin farklı inference ekosistemlerine taşınmasını sağlayan somut ilgi göstergeleri olarak listeliyor.

OpenSquilla, CLI, Web UI ve chat kanallarında çalışan, farklı LLM sağlayıcılarını ve araç kullanımını ortak bir agent döngüsünde birleştiren bir AI agent yazılımıdır.

Neden yükseliyor · 144 günde 7.059 yıldıza ulaşması ve son 28 günde 268 commit ile 9 farklı yazarın katkı vermesi güçlü ilgi ve kayda değer geliştirme etkinliği gösteriyor. Token maliyeti, model yönlendirme ve farklı kanallarda agent çalıştırma güncel ve somut ihtiyaçlar; ancak bu ölçümler tek başına ürün kalitesini veya benimsenme düzeyini kanıtlamaz.

kimi-k3-in-c, Kimi K3 modelinde inference çalıştırmayı hedefleyen bağımlılıksız bir C99 motorudur.

Neden yükseliyor · 57 günde 8.683 yıldız alması ve Kimi K3'ü 8 GB RAM'li CPU'da çalıştırma iddiası dikkat çekiyor; ancak son 28 gündeki 12 commit'in tek yazardan gelmesi, ilginin bağımsız teknik doğrulama veya geniş katkıcı tabanıyla desteklendiğini göstermiyor.

Confucius4-TTS: a Multilingual and Cross-Lingual Zero-Shot TTS Engine

Don't memorize ML. Understand it from first principles including Inference, Cuda, Deep Learning, Data Science and Reinforcement Learning

Fizgig — LoRA & Fine-tune Studio for Klein 9B, Krea 2, MiniMax H3, Qwen Image 2.1, Anima & Z-Image Turbo and Ace-Step XL: train, fine-tune,

Bilingual (中文+EN) ML / LLM / diffusion / agent interview cheat sheets for AI 秋招 — generated by ARIS /interview-cheatsheet, rendered by /rend

Autumn-Recruit Algo Notes(秋招算法学习仓库)，面向大模型时代的算法、工程与AI学习共建仓库。从数学基础、数据结构，到机器学习、深度学习、LLM、Agent、AI-Infra、语音与数据科学，通过「理解→推导→手写 → 运行 → 验证 → 复盘构建可持续迭

Full-stack open-source AI engine for building language models — tokenizer training, transformer architecture, cognitive reasoning and chat p

AI Auto Annotation & YOLO Training Pipeline, End-to-end object detection auto-labeling and YOLO training platform. VLM-powered annotation wi

Custom APRL machine-learning algorithm + a curated ML knowledge base of 923 papers, lectures, and explainers. NumPy classifier/regressor, te

Interactive desktop app with 51 labs covering ML fundamentals, transformers, RAG, agents, fine-tuning and quantization and more.

🌟 推理王国：关于 AI 推理机制的思想实验手册。从信息论、符号逻辑与表示学习出发，系统剖析大模型“智能”的本质。

从 MiniMind 源码读起,再延伸到现代大模型技术体系的中文学习笔记。主线逐行精读预训练 / SFT / DPO / PPO / GRPO 与训练机制;附录 17 篇进阶卷覆盖量化、投机解码、RLHF 全景、模型代际史等 MiniMind 没涉及、但进阶绕不开的主题。

A curated collection of AI learning materials

Free Course : Data, Machine Learning, Deep Learning and AI Engineering, the long way round: the math, the code, the systems and the security

Ultralytics YOLO26 quickstart for detection, instance and semantic segmentation, depth estimation, classification, pose, OBB, and tracking.

:sunrise: A comprehensive, cutting-edge open-source framework for next-generation Transformers, with compute-matched benchmarking and a plat

211 free visual cards about large language models, from tokenization to deployment. Full collection: 376 cards.

A mental-model-first field guide to Audio AI — from raw waveforms to production voice systems. Covers ASR, TTS, audio classification, Transf

GPT-2-style LLM built from scratch in C/CUDA with hand-written backprop, BPE tokenizer, FlashAttention, pretraining, and SFT.

A tiny neural-network framework in pure Go with AVX2 SIMD kernels (GOEXPERIMENT=simd)

Voynich Manuscript Decoded: Elu-Sinhala Phonetic Transcription & Vocabulary Toolkit 2026

PyTorch 기반 한국어 LLM 구현 및 학습 프로젝트

🦀 Decoder-only LLM built from scratch in pure Rust using Candle — no Python, no PyTorch. Gated DeltaNet + sparse attention, fine-grained MoE

由 AI 自动完成 AutoDL 实例开关机的 Claude Code skill，含空闲自动关机、预算核对与用量记账

An optimized handwritten digit recognition model delivering exceptional accuracy, high-speed performance, and compatibility with low-end har

First open-source implementation of Google TurboQuant (ICLR 2026) -- near-optimal KV cache compression for LLM inference. 5x compression wit

Distributed LLM inference fabric for heterogeneous local clusters. Features zero-copy SPSC ring buffers, automated tuning, and an OpenAI-com

🌹 Rose: Range-Of-Slice Equilibration PyTorch optimizer. Stateless optimization through range-normalized gradient updates.

Comprehensive illustrated notes for Stanford CS336 (Spring 2025) — Language Modeling from Scratch. Live: qihongruan.github.io/cs336/

GLM-5.2, a 744 billion parameter mixture of experts model, in a pure C inference engine: quantized to int4, experts streamed from disk, depl

🛡️ A modern, AI-powered WAF with visual forensic playback via rrweb. Protect your web apps with LLM-driven threat detection, real-time visua

Hardware-aligned latent deliberation framework decoupling System 2 continuous reasoning from System 1 autoregressive decoding.

Ultralytics YOLOv8 discovery and quickstart for detection, segmentation, classification, pose, OBB, and tracking.

7 Days to Die Trainer 2026: Survival Stats and Inventory Editor Guide

Ultimate 7 Days To Die Survival Stats Editor & Item Modifier 2026

AI crypto trading bot with deep neural network (84.9% accuracy, 25 coins). BiLSTM + Attention trained on GPU. Bybit, Binance, OKX, Gate.io.

AI Image Generator is a powerful and user-friendly desktop application designed to help creators produce stunning, high-quality artwork, pho

Agent Skills for small-molecule and protein therapeutics: cheminformatics, molecular ML, docking and dynamics, protein design platforms, and

End-to-end pipeline for seeing how LLMs actually process your prompts. Capture attention across every layer, render heatmaps and cooking cur

Biologically-grounded adversarial training platform: cyclic Wake/Dream/Nightmare/Compress phases that accumulate model robustness without ca

Transformers for decision models: fine-tune, load and serve calibrated decsion-model on any Hugging Face model.

This repo is a alternative solution for standard self-attention. It uses tree routing with learnable functions for cheaper self-attention wh

Readable implementation of Mamba 3 SSM model

Ultralytics YOLO11 discovery and quickstart for detection, segmentation, classification, pose, OBB, and tracking.

Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining (ICML2026)

A native macOS lab for teaching tiny language models to think — build the architecture, train the weights, and watch a small LLM emerge from