one-lithe-rune
I do JavaScript, Python, Gradio & FastAPI for AI front ends here, I do Ruby/Rails & Postgresql at work, and in another life I did React, C# and SQL Server
Mesomorphic LtdScotland
Pinned Repositories
SHARK
SHARK - High Performance Machine Learning Distribution
Auto-GPT
An experimental open-source attempt to make GPT-4 fully autonomous.
ComfyUI
A powerful and modular stable diffusion GUI with a graph/nodes interface.
continue-kobold
⏩ Continue is an open-source autopilot for VS Code and JetBrains—the easiest way to code with any LLM
diffuser-dials
The start of a Stable Diffusion UI for multiple backends
dspy
Stanford DSPy: The framework for programming—not prompting—foundation models
KoboldAI-Client
koboldcpp-rocm
A simple one-file way to run various GGML models with KoboldAI's UI with AMD ROCm offloading
llm-processing-unit
A small Python library that treats a connection to an LLM as if it were analogous to the ALU of a very simple 8-Bit style processor of yore
one-lithe-rune's Repositories
one-lithe-rune/Auto-GPT
An experimental open-source attempt to make GPT-4 fully autonomous.
one-lithe-rune/ComfyUI
A powerful and modular stable diffusion GUI with a graph/nodes interface.
one-lithe-rune/continue-kobold
⏩ Continue is an open-source autopilot for VS Code and JetBrains—the easiest way to code with any LLM
one-lithe-rune/diffuser-dials
The start of a Stable Diffusion UI for multiple backends
one-lithe-rune/dspy
Stanford DSPy: The framework for programming—not prompting—foundation models
one-lithe-rune/KoboldAI-Client
one-lithe-rune/koboldcpp-rocm
A simple one-file way to run various GGML models with KoboldAI's UI with AMD ROCm offloading
one-lithe-rune/langchain
⚡ Building applications with LLMs through composability ⚡
one-lithe-rune/lite.koboldai.net
A zero dependency web UI for KoboldAI Horde
one-lithe-rune/llama-cpp-python
Python bindings for llama.cpp
one-lithe-rune/llama_index
LlamaIndex (GPT Index) is a project that provides a central interface to connect your LLM's with external data.
one-lithe-rune/llm-processing-unit
A small Python library that treats a connection to an LLM as if it were analogous to the ALU of a very simple 8-Bit style processor of yore
one-lithe-rune/SHARK
SHARK - High Performance Machine Learning for CPUs, GPUs, Accelerators and Heterogeneous Clusters
one-lithe-rune/upscayl
🆙 Upscayl - Free and Open Source AI Image Upscaler for Linux, MacOS and Windows built with Linux-First philosophy.
one-lithe-rune/SHARK-Turbine
Unified compiler/runtime for interfacing with PyTorch Dynamo.
one-lithe-rune/stable-diffusion.cpp
Stable Diffusion in pure C/C++