koboldcpp

This contains Text-To-Speech models for use in KoboldCpp. For OuteTTS: You'll need 2 models, one OuteTTS model and one WavTokenizer. For Kokoro, Parler or Dia: Download the respective model and load it into the TTS model in koboldcpp. You do not need a wavtokenizer.

This repo contains GGUF .mmproj files intended for use in KoboldCpp alongside other GGUF models. Please pick the correct projector model to load for your architecture (e.g. all Mistral 7B based models should use the Mistral 7B projector.) Load them in KoboldCpp with `--mmproj` or from the "Model Files" tab When enabled, make sure you refresh KoboldAI Lite, then click Add Img and upload your image. Clicking that image should show Vision is enabled.

This repository contains KoboldCpp Quick Launch Templates. What are .kcppt files? .kcppt files are configuration templates that store KoboldCpp launcher preferences and settings, and model download urls. When loaded, they will find and download the necessary files automatically to get the model up and running. How to use? Simply download the kcppt file and load it in koboldcpp and then launch. Everything else is automatically downloaded. You can save and load them into the GUI, or run them directly with the --config flag.