# Multi-stage training

OLMo 2 32B is the largest 32B-parameter model in the open language model series released by the Allen Institute for AI (AI2). It is open-sourced under the Apache 2.0 license and supports English language processing.

An open-source large language model optimized for Ukrainian, built through a three-stage training process including fine-tuning, model merging, and direct preference optimization

This is a Hebrew embedding model based on sentence-transformers, capable of mapping sentences and paragraphs into a 768-dimensional dense vector space, suitable for tasks such as clustering or semantic search.

This is a Korean sentence embedding model trained on KLUE/NLI and KLUE/STS datasets, utilizing the sentence-transformers framework and optimized for sentence similarity tasks through two-stage training.