2 papers
cs.CL2025
GigaEmbeddings: Efficient Russian Language Embedding Model
Egor Kolodin, Daria Khomich, Nikita Savushkin +2
We introduce GigaEmbeddings, a novel framework for training high-performance Russian-focused text embeddings through hierarchical instruction tuning of the decoder-only LLM designe…
cs.CL2025
GigaChat Family: Efficient Russian Language Modeling Through Mixture of Experts Architecture
GigaChat team, Mamedov Valentin, Evgenii Kosarev +31
Generative large language models (LLMs) have become crucial for modern NLP research and applications across various languages. However, the development of foundational models speci…