From Bytes to Borsch: Fine-Tuning Gemma and Mistral for the Ukrainian Language Representation

Documenti analoghi

• Benchmarking Multimodal Models for Ukrainian Language Understanding Across Academic and Cultural Domains
  di: Paniv, Yurii, et al.
  Pubblicazione: (2024)
• From English-Centric to Effective Bilingual: LLMs with Custom Tokenizers for Underrepresented Languages
  di: Kiulian, Artur, et al.
  Pubblicazione: (2024)
• Achieving Tokenizer Flexibility in Language Models through Heuristic Adaptation and Supertoken Learning
  di: Sharthak, Shaurya, et al.
  Pubblicazione: (2025)
• Beyond Uniform Credit: Causal Credit Assignment for Policy Optimization
  di: Khandoga, Mykola, et al.
  Pubblicazione: (2026)
• Empowering Smaller Models: Tuning LLaMA and Gemma with Chain-of-Thought for Ukrainian Exam Tasks
  di: Syromiatnikov, Mykyta, et al.
  Pubblicazione: (2025)