Havuz

Generative image and video runtimes for Apple Silicon (MLX): text/image-to-image, instruction editing, masked edit, text/image/reference-to-

ML model ports (ASR · TTS · LLM · VLM · vision · audio codecs) on the rlx multi-backend compiler + runtime — CPU/Metal/MLX/CUDA/wgpu

Companion code for the Manning book 'LLM Customization and Fine-Tuning.' Adapt open-weights LLMs end to end: prompting and RAG, LoRA/QLoRA,

Tiny-MoE is a lightweight Mixture-of-Experts language model built entirely from scratch in native PyTorch and trained end-to-end on Kaggle u

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

One GPU. Full LLM workflow. Real benchmarks. No cloud required.

A user's facts become a few rows in a content-addressed memory table — not a rewrite of the model. Paper, code, data, and interactive site f

Local-first social memory search engine with browser capture, hybrid AI retrieval, and optional C++ acceleration.

A narrative walk through 90 years of AI history, paper by paper. 66 chapters from Turing 1936 to Blackwell 2025.

ABTFarmer - Angry Birds Transformers farmer with automated time-skip glitch

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

Recomputation-free, context-independent KV caching for large language models

Pareto-optimal models for cleaning the web — fast, encoder-based main-content extraction from HTML.

本地 AI 驱动的实时对话翻译桌面应用（Real time dialogue translation desktop application driven by local AI）

A native .NET LLM inference engine and agent runtime for GGUF models. TensorSharp provides a console application, a web-based chatbot interf

A free, open GenAI curriculum built from scratch. Start from zero, build real projects, and work your way up to production AI systems.

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

First open-source TurboQuant KV cache compression for LLM inference. Drop-in for HuggingFace. pip install turboquant.

Model merging, task-vector rebasin, and fine-tuning for vision and LLM models.

MCore-Bridge: Providing Megatron-Core model definitions for state-of-the-art large models and making Megatron training as simple as Transfor

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

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