# Multi-task optimization

Instella-Long is an open-source language model with 3B parameters developed by AMD, supporting a context length of 128K and performing excellently in long-context benchmark tests.

xGen-small is an enterprise-grade compact language model that achieves long-context performance with predictable low costs through domain-focused data curation, scalable pre-training, length extension, and reinforcement learning fine-tuning.

This is a pre-trained language model merged using the SLERP method, combining the characteristics of both Captain-Eris_Violet-GRPO-v0.420 and MMR-E1 models.

A 32B-parameter large language model constructed based on the SCE fusion method, integrating multiple high-performance pre-trained models

High-quality Russian sentence embedding BERT model, optimized based on cointegrated/LaBSE-en-ru, suitable for semantic text similarity tasks

LERT is a linguistics theory-driven pre-trained language model designed to enhance model performance through linguistic knowledge.

GottBERT is the first RoBERTa model specifically designed for German, pre-trained on the German portion of the OSCAR dataset, available in both base and large versions.

BERT model pre-trained on 300G Chinese corpus using MLM, POS, and SOP tasks