Arcee's MergeKit: A Toolkit for Merging Large Language Models

arXiv:2403.13257v1 Announce Type: cross
Abstract: The rapid expansion of the open-source language model landscape presents an opportunity to merge the competencies of these model checkpoints by combining their parameters. Advances in transfer learning, the process of fine-tuning pre-trained models for specific tasks, has resulted in the development of vast amounts of task-specific models, typically specialized in individual tasks and unable to utilize each other's strengths. Model merging facilitates the creation of multitask models without the need for additional training, offering …

arcee arxiv cs.ai cs.cl cs.lg language language models large language large language models merging toolkit type