BoCoEL is an open-source tool that leverages Bayesian optimization to efficiently evaluate large language models by selecting a small, meaningful subset of test data. It encodes entries into embeddings and optimizes evaluation coverage, reducing resource usage for researchers and model evaluators. The project is now archived.
BoCoEL is a LLM eval & observability product. It focuses on reducing the computational cost and time of evaluating large language models by selecting optimal test subsets using Bayesian optimization. It is built as an open-source project for AI researchers and model evaluators. BoCoEL is open source under the BSD-3-Clause license. The product ships for API.
BoCoEL first shipped in 2023. Development happens publicly on GitHub with 289 stars and 1 commits in the last 90 days. Key capabilities include bayesian optimization, corpus selection, and model evaluation. The product is being sunset.
Latest indexed changes and source events
Other apps tracked under the same category.
