Ultra-Instruct-12B

Papers using or citing this model 2

• TIES-Merging: Resolving Interference When Merging Models 1K citations · 2023 · arXiv

  Transfer learning - i.e., further fine-tuning a pre-trained model on a downstream task - can confer significant advantages, including improved downstream performance, faster convergence, and better sample efficiency. These advantages...

• Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch · 2023 · arXiv

  In this paper, we unveil that Language Models (LMs) can acquire new capabilities by assimilating parameters from homologous models without retraining or GPUs. We first introduce DARE to set most delta parameters (i.e., the disparity...