-
Qualitatively characterizing neural network optimization problems
Paper • 1412.6544 • Published • 4 -
Convergent Learning: Do different neural networks learn the same representations?
Paper • 1511.07543 • Published • 2 -
Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models
Paper • 1909.11299 • Published • 2 -
Model Fusion via Optimal Transport
Paper • 1910.05653 • Published • 1
Collections
Discover the best community collections!
Collections including paper arxiv:1412.6544
-
Qualitatively characterizing neural network optimization problems
Paper • 1412.6544 • Published • 4 -
Averaging Weights Leads to Wider Optima and Better Generalization
Paper • 1803.05407 • Published • 2 -
Merging Models with Fisher-Weighted Averaging
Paper • 2111.09832 • Published • 1 -
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
Paper • 2203.05482 • Published • 6
-
google-bert/bert-base-uncased
Fill-Mask • Updated • 86.7M • • 2.17k -
sentence-transformers/embedding-training-data
Updated • 1.04k • 122 -
PygmalionAI/pygmalion-6b
Text Generation • Updated • 4.16k • 745 -
Qualitatively characterizing neural network optimization problems
Paper • 1412.6544 • Published • 4