The model was built on the basis of Gigachat-3B and a three-stage training was performed: front, fine tuning and mulizadak. The architectural was optimized, which made it possible to reduce the volume of the parameters quarter without deteriorating quality. Gigaembeddings can already be used in gitvert and huggingfece.
The market still lacks effective solutions to work with Russian language. Most of the existing vehicles required important resources or gave weak results in the processing of texts. The new model closes this gap and offers a universal tool for various industries.
Gigaembeddings is particularly important for a correct analysis of user queries and is suitable for creating smart chat boots and RAG systems for example in banks.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
