Stars
An sdk and framework for evaluating and comparing multiple model outputs using configurable LLM-based jurors
Evaluating LLM with swappable judges: local, remote, openrouter on multiple benchmarks.
ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program Evolution 🧬
An open, end-to-end implementation of TabPFN-like foundation models, covering synthetic priors/data, training, and evaluation on TabArena.
A simple implementation for embarassingly parallel for which supports native multiprocessing, joblib and ray as backend.
A system for easily loading and running thousands of DOS programs on vintage hardware
Curated list of datasets and tools for post-training.
Open source LLM arena created by the French Government
A Playground for Tabular Foundation Models
Merge of megatron-train, autoexperiment and oellm_pretrain.
Lightweight and educational reimplementation of TabPFN https://arxiv.org/pdf/2511.03634
A python module implementing interfaces for various public tabular priors
Access large language models from the command-line
From a+b to sparsemax(QK^T)V in Triton!
Scripts and instructions for replicating the original FineWeb experiments on LUMI
Official Repository for HOLLM "Hierarchical Optimization with Large Language Models"
Large scale and asynchronous Hyperparameter and Architecture Optimization at your fingertips.
Stock options, RSUs, taxes — read the latest edition: www.holloway.com/ec