Self-evaluating interview for AI coders

Single Request Batching API server backed by llama.cpp

ModelZoo is a system for managing and serving local Large Language Models (LLMs).

Async Generative Workflows Manager

🐸 A non-linear AI-enabled text editing environment

Join multiple local LLM API servers to the AI Horde

Experimental LLM Inference UX to aid in creative writing

Simple Synthetic Data Generation with LLMs

Too Long, Didn't Watch: End-to-End Rolling Summarizer of Long Videos

Large Language Models playing Tic-Tac-Toe against each other

Automated proxy to merge multiple LLM endpoints into one

Synthetic LLM Conversation Analyzer

Tcurtsni: Reverse Instruction Chat, ever wonder what your LLM wants to ask you?

Scripts to make the Dell R730 behave properly with Nvidia Pascal P40 and other datacenter GPUs

Next-generation LLM Performance Benchmarking

Use llama.cpp server to join the AI Horde

Evolution/Genetic Algorithms applied to finding ideal LLM Sampling Parameters

jQuery, React and Streamlit applications written by LLMs

Experimental sampler to make LLMs more creative

Simple, Fast, Parallel Huggingface GGML model downloader written in python

Training a micro transformers model from scratch to write "Bluey" episodes

Interactive LLM weight explorer made with Streamlit

Scripts to parse rosettacode scrape into structured data

Python examples using the bigcode/tiny_starcoder_py 159M model to generate code