Havuz

Master LLM Fine-Tuning Trainer 2026: Advanced NLP Optimization Toolkit

Token Cost Parity: Multilingual LLM Efficiency Analysis 2026

Somali NLP Corpus is an open, high-quality Somali text corpus designed to support research and development in Natural Language Processing (N

Humanize KR, Korean AI metinlerindeki çeviri kokan ve mekanik ifade kalıplarını tespit edip LLM yardımıyla daha doğal bir üslupla yeniden yazan bir CLI skill’idir.

Neden yükseliyor · 156 günde 5.711 yıldız alması belirgin ilgiye işaret ediyor; son 28 günde 57 commit ve 9 farklı yazar da projenin güncel katkı aldığını gösteriyor. Korean diline odaklanması ve birden fazla CLI ortamını desteklemesi ilgiyi artırmış olabilir; veriler tek başına yükselişin nedenini kanıtlamaz.

The open, machine-readable standard for the Somali language — orthography, grammar, terminology, translation, and AI/benchmark resources, as

Build & Auto-Optimize LLM Apps in 2026: The Ultimate AdalFlow Guide

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。

📚 Read a top-tier AI paper in 5 minutes.

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

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

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

natural-japanese, AI agent’ların iş amaçlı Japonca metinleri daha okunaklı yazıp gözden geçirmesine yardımcı olan bir Agent Skill ve lint araçları sunar.

Neden yükseliyor · 78 günde 1.748 yıldıza ulaşması, AI ile üretilen Japonca metinlerin niteliğine dönük ilginin güçlü olduğuna işaret ediyor; birden fazla agent ortamında kurulabilmesi de erişimini genişletiyor. Ancak bu ölçümler ilginin nedenini kanıtlamıyor; son 28 günde 5 commit ve 1 farklı yazar görülmesi de geliştirme faaliyetinin dar bir katkıcı çevresinde olduğunu gösteriyor.

AI tarafından üretilen metni LLM yeniden yazımları ve farklı makine çevirisi servisleriyle yeniden yapılandıran, yerelde çalıştırılabilir bir Python pipeline'ıdır.

Neden yükseliyor · 132 günde 2.979 yıldıza ulaşması belirgin ilgiye işaret ediyor; son 28 gündeki 21 commit ve 4 farklı yazar da projenin güncel olarak geliştirildiğini gösteriyor. Bu veriler ilgi ve aktivite kanıtıdır, çıktının kalitesi veya iddia edilen etkinliği için bağımsız kanıt değildir.

📚 数千篇 AI、LLM、NLP、CV 顶会论文解读，每篇 5 分钟读懂核心思想。

Adaptive Chunking: automatically select the best chunking method per document for RAG. Accepted at LREC 2026.

Buddhist Digital Text Platform — 10,500+ texts, 613 sources, trilingual cross-canon, AI Q&A (RAG), knowledge graph, full-text search

Free, open-source AI writing humanizer and detector. 55 patterns, 5 voices, a 0-100 AI-tell score, and nothing leaves your machine.

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

Translate between English and Claudish with tiny ProgramAsWeights functions.

All Jina AI APIs as Unix CLI commands. Search, read, embed, rerank - with pipes.

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

Online-adaptive multi-agent framework for enterprise API orchestration. Adaptive circuit breakers, SLA-driven routing, hybrid LLM+rule inten

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

中文敏感词/违禁词检测 MCP Server | 支持小红书/抖音/快手/B站 | 风险分级+安全替换建议 | 微信: chenganp | 邮箱: 345048305@qq.com

A compounding LLM-wiki, best fit as a personal second brain that organizes and updates itself as it grows, zero upkeep.

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

Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models

A locally-running multi-agent human in the loop system for deep, interdisciplinary research with only 4 dependencies.

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

A post-retrieval temporal layer for RAG systems — validity filtering, time decay, document kind classification, and hybrid reranking in one

a LLM inference engine to run on consumer hardware

Teknofest 2026 Doğal Dil Ajanları Yarışması 1. Senaryo kapsamında geliştirilen, kamu sektörü için resmi evrak analizi ve taslak üretimi yapa

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

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

First open-source AI knowledge layer for Togo - 62K+ documents, RAG API, fine-tuned LLM. Built for developers, startups and institutions i

Detect hallucinations in LLM responses. Verify every claim against source documents using hybrid STS + NLI. Works with LangChain, LlamaIndex

🔍 Detect AI-generated text and fingerprint which LLM wrote it. Open-source GPTZero alternative. Zero dependencies, works offline.

A high-accuracy, multilingual rule-based Sentence Boundary Detector (SBD) with a drop-in adapter for pysbd, delivering faster and more accur

LLM-powered conversation summarisation service for OCTO — turns group chats and threads into structured briefs with key decisions, open ques

SomNLP-Translate is an open, high-quality English–Somali parallel dataset designed to support research and development in machine translatio

Turn documents into high-quality instruction datasets with grounding, quality filtering, deduplication, and provenance.

A pure-Python structured memory benchmark for multi-agent LLM systems — context graph vs vector RAG vs raw history dump, five scenarios, 18

A free, privacy-first tool that flags the tells of AI-generated writing, overused vocabulary, rhetorical crutches, robotic sentence rhythm a

Train linear embedding adapters with triplet loss to align retrieval embeddings with your queries (RAG).

Python SDK for LLM guardrails with safety classification, PII detection, prompt injection defense, and grounding checks. Protect AI applicat

Locally fine-tuned Russian RAG models: document splitter, query expansion, retrieval embedder. Teacher distillation → GGUF → llama.cpp on AM

LLM-free, layout-aware PDF chunking for RAG pipelines. Preserves document structure via regex and font heuristics. Written in pure Rust.

A structured knowledge base for large language model technologies, covering LLMs, Agents, RAG, model training, evaluation methodologies, and

A zero-allocation, header-only C++ BPE tokenizer for Qwen, built for maximum inference throughput.