tartuNLP/Llammas-base-p1-GPT-4o-human-error-mix-paragraph-GEC

tartuNLP/Llammas-base-p1-GPT-4o-human-error-mix-paragraph-GEC is a grammatical error correction (GEC) model developed by tartuNLP, specifically designed for paragraph-level error correction in Estonian. This model is part of a pipeline that processes an entire paragraph as input and outputs the corrected text. It leverages synthetic training data generated by proprietary large language models to address the scarcity of Estonian error correction and explanation data, making it particularly useful for educational applications and learners of Estonian.