Havuz

OpenMythos, Claude Mythos’un gerçek mimarisini temsil ettiği kanıtlanmayan, araştırma literatürüne dayalı varsayımsal bir Recurrent-Depth Transformer uygulamasıdır.

Neden yükseliyor · Claude Mythos’a doğrudan atıf yapan adı ve açıklaması, varsayımsal mimariyi incelemek isteyenlerin ilgisini çekmiş olabilir; 162 günde 14.904 yıldız bu ilgiyi gösteriyor. Bu, benimseme veya teknik doğrulama kanıtı değil: son 28 günde commit ve farklı yazar sayısı sıfır.

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

Local AI BGM and sound effects for Claude Code and any MCP client. Stable Audio 3 on Apple Silicon (MLX) and Windows NVIDIA GPUs (PyTorch).

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.

Halo is an open-source framework built by White Circle for training large language and multimodal models

本地优先的全栈 AI 创作工作站：AI对话 · AI漫画 · 漫剧创作 · 写作台 · 知识学习五大模块；vLLM / llama.cpp / Transformers 多引擎本地推理，显存智能调度、舱壁隔离自愈、仅供学习使用，欢迎交流指正。（最新进度（除插件系统）受到协议限制，

🚀🚀 A multimodal System One decision model that gives calibrated answers to typed questions about screens, photos, video and text in one forw

Refusal removal as a loadable KV-cache graft — zero weight modification, no refusal-direction projection, fully reversible.

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

Phonon: open speech recognition models (Phonon-2, Phonon-1) — CLI, CPU and CUDA images

This project is for learning: it shows how an agent loop works underneath, in a way more intuitive and visual than reading about it. Behind

Single-GPU LLM fine-tuning preflight: memory estimates, runnable LoRA/QLoRA recipes, and local measurements.

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

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

From teacher to tiles — a from-scratch LLM distillation & serving engine: custom Triton/CUDA kernels, FSDP distillation, paged-KV continuous

Local decision engine with typed, calibrated outputs (Noul/Choice/Score): cheap→strong cascade, ECE/Brier calibration, SystemOne protocol in

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

Iris-3B pixel-space text-to-image on Apple Silicon GPUs: Metal-optimized engine, native macOS app, CLI, Python and local HTTP API

Jacobian-Brainwash : A manual alignment tool for large language models built on Anthropic's Jacobian Lens. Results are exportable.

To know what models don't say out loud.

🔥🔥 Accelerating decision inference with exact state forking

Scaler 2 Music Theory Tool 2026: Direct DAW Integration for Windows 10 and 11

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。

PyTorch 기반 한국어 LLM 구현 및 학습 프로젝트

Full-featured DAW, DJ, and VJ app interoperable w/Ableton, Reaper, Resolume & more. Stable Audio 3, Magenta RT2, Suno API, Chimera track fus

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

Qwen-Image-2.1 ile Apple Silicon üzerinde yerel görsel üretimi ve çoklu görsel düzenleme sağlayan bir CLI ile helmstudio’ya bağlı web arayüzü sunuyor.

Neden yükseliyor · Beş günlük yaşında 55 yıldız ve son 28 günde 12 commit, iki farklı yazar görünüyor. Bu ilk ilgi ve geliştirme hareketliliğine işaret ediyor; ancak kısa geçmiş ve sınırlı yazar sayısı benimsenme ya da kalıcı bakım kanıtı değil.

From PyTorch model to end-to-end TensorRT inference experience in two commands—AI-native, cross-platform, and built for the best possible us

Official code for Echo-Memory: a controlled study of memory in action-conditioned video world models (Context, Compression, Spatial, State-S

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

Best AI Workload Orchestrator for Kubernetes Python 2026

Windows utility focused on cuda setup, nvidia local AI, and cuda environment for local AI workflows.

Streamline AI Workloads on Kubernetes: Universal Python SDK Guide 2026

Automated alignment adjustment for LLMs — direct steering, LoRA, and MoE expert-granular abliteration, optimized via multi-objective Optuna

Lev: Thinking Fast and Deep with Looped Decision Models. One checkpoint, multiple depths: System 1.5 decision models that think in loops, no

Offline multi-speaker meeting-speech toolkit: planted-ground-truth synthetic meeting factory, VAD, speaker embeddings, diarization (AHC/spec

Open, calibrated System 1 decision models: typed choice / score / yes-no answers with a probability for every option. 400M to 80B; CPU, NVID

Self-Tuning Multi-Agent AI Trading System 2026: 8-Source Signal Fusion & Kronos Model

A curated collection of AI learning materials

Tiny local text-to-24x24 pixel art model, trained on roughly 200K samples in 30 minutes on an RTX 5090.

Train JEV-style System 1 decision models on Qwen3.5 and Qwen3.8-27B: 24-slot decision head, KL distillation, calibration and serving. 在 Qwen

A self-hosted studio for generating images, video, and audio with diffusion models.

Official Implementation of LongLive-RAG: A general retrieval-augmented framework for long video generation.

Split FLUX.2 and LTX 2.3 across two GPUs (LAN or same-machine) — NVENC compresses activations live on the wire. Icarus (ComfyUI node) + Daed

[Preprint] TBSM: Three-Body Scattering for Generative Modeling.

The htop for LLM inference see exactly where every GB of VRAM goes and get measured quantization savings.

A small chat model trained from scratch: tokenizer → pretraining → SFT → RL → multimodal. 0.78B params, CORE 0.248, tool calling, vLLM. Weig

Building a small LLM in PyTorch from scratch - a step-by-step journey inspired by Stanford CS336.

Tiny, fast Brazilian Portuguese text-to-speech (21M params)

STEER — AI4R (AI for Research) experiment framework for auto-research and autonomous research. Connect existing research projects and let an