gordicaleksa/serbian-llm-eval

Serbian LLM Eval.

36
/ 100
Emerging

This project helps evaluate how well large language models (LLMs) understand and generate Serbian text. It takes an LLM (such as one you've developed or are considering using) as input and provides performance scores across various tasks like common sense reasoning, world knowledge, and reading comprehension. This is useful for researchers and developers working on building or deploying LLMs tailored for the Serbian language and potentially other Serbo-Croatian-Bosnian (HBS) languages.

No commits in the last 6 months.

Use this if you need to objectively measure the capabilities of an LLM in Serbian, specifically for tasks like understanding context, answering questions based on general knowledge, and comprehending text.

Not ideal if you are looking to evaluate an LLM's performance in complex areas like advanced mathematics, coding, or aggregated benchmarks like MMLU and BBH, as these are not yet covered.

natural-language-processing serbian-language llm-evaluation ai-development language-model-benchmarking
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

97

Forks

8

Language

Python

License

Last pushed

Mar 19, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/gordicaleksa/serbian-llm-eval"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.