A free, offline, and openly licensed Japanese-to-English dictionary. Updates weekly!

Japanese pop-up dictionary browser extension. Successor to Yomichan.

Manga OCR snipping application for desktop

Upscale manga with AI models

Popular Node.js module for parsing JavaScript objects into XML

Plugins and utilities for Zod

A SOAP client and server for node.js.

A simple & customizable no-frills Minecraft chat system

Spigot plugin enabling two-way chat messaging between Minecraft and Discord

macOS System-wide Audio Equalizer & Volume Mixer 🎧

my styles for the darktable raw developer

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference,…

Implementation for MatMul-free LM.

Collection of film emulation presets for open-source RAW developer software Darktable.

Build-your-own Valheim build for macOS

The fastest way to develop full-stack web apps with React & Node.js.

Lists and configuration for our DNS blocking service

ISA_I 2024/2025 @ FIIT STU in Bratislava

A Unified Library for Parameter-Efficient and Modular Transfer Learning

🦜🔗 Build context-aware reasoning applications

Code for the paper Hybrid Spectrogram and Waveform Source Separation

A curated list of neural network pruning resources.

[NeurIPS 2023] LLM-Pruner: On the Structural Pruning of Large Language Models. Support LLaMA, Llama-2, BLOOM, Vicuna, Baichuan, etc.

Tools for merging pretrained large language models.

SiLLM simplifies the process of training and running Large Language Models (LLMs) on Apple Silicon by leveraging the MLX framework.

Make huge neural nets fit in memory

OpenBA-V2: 3B LLM (Large Language Model) with T5 architecture, utilizing model pruning technique and continuing pretraining from OpenBA-15B.

Automated Identification of Redundant Layer Blocks for Pruning in Large Language Models