Havuz

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

多模态检索实战：意图识别、Prompt 工程、Qwen LoRA、EmbeddingGemma 2 与 InfoNCE 对比学习。含真实演示、自有数据接入、训练评测及 RAG 检索组件学习指南。

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).

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

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

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，

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.

🚀🚀 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.

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

🔥🔥 Accelerating decision inference with exact state forking

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

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

结合预训练编码器、BiLSTM 与 GlobalPointer 的实体关系联合抽取模型，支持标注校验、训练、评估及三元组预测。

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

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

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

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

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

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

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

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.

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

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

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

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

Build world models from scratch — from perception and latent dynamics to planning, JEPA, VLA, and 3D/4D intelligence.

🔥 AI agent that ports CUDA code to AMD ROCm using local LLMs — FastAPI + React + Ollama | Live: rocmporter-agent.vercel.app

[ICML 2026] NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models

A modern, hands-on, self-paced course that takes you from your first line of Python to shipping a real AI-powered automation.

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

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

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

Evaan — a fully local, offline-capable AI companion chatbot built with Python & Hugging Face Transformers, running on Qwen2.5-0.5B-Instruct

One embedding space for text, image, video, audio, thermal, motion, and touch. Open weights, self-hostable.

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.

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

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

Production-ready, bleeding-edge, upstream-first vLLM Docker image for the NVIDIA DGX Spark (GB10 / sm_121a), verified against real models on

Implementation of LatentMoE,Toward Optimal Accuracy per FLOP and Parameter in Mixture of Experts (Elango et al., NVIDIA 2026) — in Pytorch.

Official implementation of "Unifying Distributional Training for One-Step Visual Generation" (MGFlow).

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

To know what models don't say out loud.

A curated collection of AI learning materials

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

Self-tuning multi-agent AI trading system. 8-source signal fusion, Bull/Bear/Judge debate on Claude Opus 4.7, Kelly + ATR position sizing. P

Open-source Environment toolkit of claw-like agents, support task/harness generation and evaluation

Best AI Workload Orchestrator for Kubernetes Python 2026

Inference engine for large language models on consumer GPUs, with deep optimization for older hardware