model merging
A process of combining multiple AI models, often to create a more robust or generalized model by aggregating knowledge from different sources. This is useful in scenarios like ensemble learning.
- Activation-Guided Consensus Merging for Large Language Models
- Activation-Informed Merging of Large Language Models
- Continual Model Merging without Data: Dual Projections for Balancing Stability and Plasticity
- Curriculum Model Merging: Harmonizing Chemical LLMs for Enhanced Cross-Task Generalization
- FlexOLMo: Open Language Models for Flexible Data Use
- HM3: Hierarchical Multi-Objective Model Merging for Pretrained Models
- MergeBench: A Benchmark for Merging Domain-Specialized LLMs
- Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging
- Model Merging in Pre-training of Large Language Models
- Train with Perturbation, Infer after Merging: A Two-Stage Framework for Continual Learning