The Structural Scalpel: Automated Contiguous Layer Pruning for Large Language Models
"层剪枝" 相关文章
When Fewer Layers Break More Chains: Layer Pruning Harms Test-Time Scaling in LLMs
Enabling Differentially Private Federated Learning for Speech Recognition: Benchmarks, Adaptive Optimizers, and Gradient Clipping
PruneCD: Contrasting Pruned Self Model to Improve Decoding Factuality
