EPFL Machine Learning and Optimization Laboratory
- 307 followers
- Lausanne, Switzerland
- http://mlo.epfl.ch
Popular repositories Loading
-
OptML_course
OptML_course PublicEPFL Course - Optimization for Machine Learning - CS-439
-
attention-cnn
attention-cnn PublicSource code for "On the Relationship between Self-Attention and Convolutional Layers"
-
landmark-attention
landmark-attention PublicLandmark Attention: Random-Access Infinite Context Length for Transformers
-
Repositories
Showing 10 of 55 repositories
- getting-started Public
epfml/getting-started’s past year of commit activity - llm-baselines Public
epfml/llm-baselines’s past year of commit activity - personalized-collaborative-llms Public
Exploration on-device self-supervised collaborative fine-tuning of large language models with limited local data availability, using Low-Rank Adaptation (LoRA). We introduce three distinct trust-weighted gradient aggregation schemes: weight similarity-based, prediction similarity-based and validation performance-based.
epfml/personalized-collaborative-llms’s past year of commit activity - error-feedback-SGD Public
SGD with compressed gradients and error-feedback: https://arxiv.org/abs/1901.09847
epfml/error-feedback-SGD’s past year of commit activity - schedules-and-scaling Public
epfml/schedules-and-scaling’s past year of commit activity
