Havuz

A computer, compiled into the weights of a language model. An exact CPU inside Qwen3.5-4B, with Gated DeltaNet state as RAM.

AnyJev, open LLM’lerden typed kararlar ve eşiklenebilir olasılıklar üretmek için calibration ve karar katmanları sunan bir Python kütüphanesidir.

Neden yükseliyor · Yedi günde 802 yıldız almış; dikkat çekmesinde etiket gerektirmeyen ilk seviye, az etiketle kalibrasyon iddiası ve modeli fine-tune etmeden karar endpoint’i sunma yaklaşımı etkili görünüyor. Bu ilgi benimseme kanıtı değil; verilen sonuçlar README’deki sınırlı benchmark’a dayanıyor.

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

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

rizzo-pii, İtalyanca hukuk metinlerindeki kişisel verileri yerel olarak tespit edip geri döndürülebilir placeholder’larla maskeleyen bir yazılımdır.

Neden yükseliyor · 91 günde 1057 yıldız ve son 28 günde 25 commit ile 5 farklı yazar görünür ilgi ve yakın dönem geliştirme faaliyeti gösteriyor; yükselişin özel nedeni mevcut verilerden doğrulanamıyor.

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

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

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

A moddable training framework for pre-training ablations.

an open-source, from-first-principles reconstruction of the ideas behind TypeSafe AI's Jev, written in pytorch

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

Transformer architecture explained step by step - the full architecture, every attention variant, positional embeddings, and every layer ins

Native AI inference for PHP 8.3+ - run ONNX, GGUF (llama.cpp) and RubixML models directly in your PHP process via FFI. Chat, streaming, embe

Interactive 3D visualization platform for exploring transformer architectures, tensors, and real-time LLM inference.

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

Open-source alternative to TypeSafe's Jev: a System One style model layer that gives typed, calibrated decisions from any open-weights LLM i

Build LLM systems you actually control. A free, open engineering book + course — from tokenization to serving your own models. Mechanisms, t

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

Runs Hugging Face ONNX models on any Nx backend, with no per-architecture code

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

Spark-optimized MLX LM for local inference and deployment on Apple Silicon

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

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

To know what models don't say out loud.

Research project on bilingual Urdu-English retrieval-augmented generation for Pakistani government and legal documents, with OCR, hybrid ret

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

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

Low-memory C++20 LLM inference runtime for quantized GGUF models on CPU — mmap-backed weights, paged KV cache, Q4/Q8 kernels, and reproducib

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

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

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

Guía gratuita de IA generativa avanzada en español (311 págs.): Transformer, post-entrenamiento, inferencia, GPU, difusión, agentes, segurid

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

Distributed 56M-parameter LLM inference across 3 ESP32-S3 boards via ESP-NOW , Split-PLE + KV cache, fully offline.

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

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

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

hummingbird is a lightweight, zero dependency runtime for massive open source Mixture of Experts (MoE) language models. It unifies SSD, RAM,

OpenAI-compatible server with a live view into any HF model's residual stream. pip install brainscope

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

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

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

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

🌟 [Survey & Benchmark] A unified taxonomy, geometric framework, and cross-domain benchmark for modern optimizers

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

AI-powered fake news detection system with multiple ML models and explainability.

Publication-quality LLM architecture figures from config.json — Raschka-style towers, diffs, posters, VRAM math. No weights needed.

🧠 One LLM, split across a Mac (Apple MPS) + a Windows PC (NVIDIA CUDA) — heterogeneous pipeline inference over a framework-neutral wire, bit

Why is LLM inference slow — and how do you make it fast? A hands-on, first-principles course: roofline → KV cache → quantization → paralleli