-
Featherless AI
- Midwest, USA
-
21:05
(UTC -05:00) - https://discord.gg/RB6HQwC2hX
- https://www.patreon.com/WayWySoftworks
Stars
🤯 Lobe Chat - an open-source, modern design AI chat framework. Supports multiple AI providers (OpenAI / Claude 4 / Gemini / DeepSeek / Ollama / Qwen), Knowledge Base (file upload / knowledge manage…
[Forge Mod] Building Tools and Aesthetic Technology
Get started quickly with Next.js, Postgres, Stripe, and shadcn/ui.
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
Inspired by Micdoodle's Galacticraft, Northstar seeks to return players to the stars with the power of the Create mod.
Space exploration, trading, and combat game.
A self-organizing file system with llama 3
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train Qwen3, Llama 4, DeepSeek-R1, Gemma 3, TTS 2x faster with 70% less VRAM.
Launcher scripts for SillyTavern and ST-Extras.
MVP of an idea using multiple local LLM models to simulate and play D&D
Scrape fandom wikis to gather data for text generation algorithms.
A low overhead rate limiter for your routes
A simple tool-use assistant for local LLMs powered by TabbyAPI
Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, Mistral Small 3.1 and other large language models.
A multimodal, function calling powered LLM webui.
🌼 🌼 🌼 🌼 🌼 The most popular, free and open-source Tailwind CSS component library
This is a Python script that scrapes the text content from stories and their chapters.
Provide large guidance scale correction for Stable Diffusion web UI (AUTOMATIC1111), implementing the paper "Characteristic Guidance: Non-linear Correction for Diffusion Model at Large Guidance Scale"
Distribute and run LLMs with a single file.
BrainFlow code that sends your brain's relaxation, focus metrics, and machine learned thought commands to vrchat avatar paramaters via OSC.
An open source ChatGPT UI.
Official implementation of Würstchen: Efficient Pretraining of Text-to-Image Models
OneTrainer is a one-stop solution for all your stable diffusion training needs.
StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation
A 99% automatized pipeline to construct training set from anime and more for text-to-image model training