Empowering Smaller Models: Tuning LLaMA and Gemma with Chain-of-Thought for Ukrainian Exam Tasks Paper • 2503.13988 • Published Mar 18, 2025 • 1
UA-Code-Bench: A Competitive Programming Benchmark for Evaluating LLM Code Generation in Ukrainian Paper • 2511.05040 • Published Nov 7, 2025
Empowering Smaller Models: Tuning LLaMA and Gemma with Chain Collection PEFT tuning on ZNO (EIE and NMT) exams with and without chain-of-thought. LLaMA 3.1 & LLaMA 3.2 models to be added. arXiv:2503.13988 • 9 items • Updated Mar 20, 2025