OpenRaiser/OmniOpt

Benchmark and optimize LLM inference across frameworks with ease

Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.

Toolkit for fine-tuning, ablating and unit-testing open-source LLMs.

Comprehensive LLM evaluation at scale: A production-ready framework for evaluating large language models across multiple benchmarks.

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

A multi-platform desktop application to evaluate and compare LLM models, written in Rust and React.

LLM that can be trained on 1 or more GPUs for research.

Building the Virtuous Cycle for AI-driven LLM Systems