henk717's repositories
ConcedoBot
A very simple Discord bot intended for KoboldCpp
KoboldAI-Horde-Bridge
Turns KoboldAI into a crowdsourced distributed cluster
lite.koboldai.net
A zero dependency web UI for KoboldAI Horde
PygDiscordBot
Discord bot that uses Alpaca models and KoboldAI
pygmalion-docs
The Pygmalion Docs
AI-Horde
A crowdsourced distributed cluster for AI art and text generation
AI-Horde-Worker
This repo turns your PC into a AI Horde worker node
aphrodite-engine
PygmalionAI's large-scale inference engine
AutoGPTQ
An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.
continue
⏩ The easiest way to code with any LLM—Continue is an open-source autopilot for VS Code and JetBrains
DiscordLangAgent
DiscordLangAgent: This is a Discord chatbot built with LangChain. It uses the 'Agents' feature in LangChain to create flexible conversation chains based on user input. The bot can interact with different language models and tools, and supports multiple API endpoints.
exllamav2
A fast inference library for running LLMs locally on modern consumer-class GPUs
jax
Modified version of jax 0.2.21
KoboldAI-TerminalBot
KoboldAI API usage example - Runs a chat interface in terminal that can also generate and display images in terminal from StableDiffusion
koboldai.com
KoboldAI Website
llmpeople
3D models powered by Koboldcpp
mergekit
Tools for merging pretrained large language models.
mesh-transformer-jax
Fork of kingoflolz/mesh-transformer-jax with memory usage optimizations and support for GPT-Neo, GPT-NeoX, BLOOM, OPT and fairseq dense LM. Primarily used by KoboldAI and mtj-softtuner.
mtj-softtuner
Create soft prompts for fairseq 13B dense, GPT-J-6B and GPT-Neo-2.7B for free in a Google Colab TPU instance
stable-diffusion-webui-a1111
Stable Diffusion web UI
stable-ui
🔥 A frontend for generating images with Stable Diffusion through Koboldcpp
talemate
Roleplay with AI with a focus on strong narration, consistent world and game state tracking.
TransformerLens
A library for mechanistic interpretability of GPT-style language models