Inar Timiryasov

3 papers · 2023–2024 · 2 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (2) 🐝 Cross-Pollinator (15)

Conferences

CONLL (2) EMNLP (1)

Top co-authors

Jean-Loup Tastet (3)

Keywords

knowledge distillation (1) language model (1) ensemble distillation (1)

Papers

BabyLlama-2: Ensemble-Distilled Models Consistently Outperform Teachers With Limited Data CONLL 2024

Baby Llama: knowledge distillation from an ensemble of teachers trained on a small dataset with no performance penalty CONLL 2023

Baby Llama: knowledge distillation from an ensemble of teachers trained on a small dataset with no performance penalty EMNLP 2023