Dill Lab at USC

community

https://dill-lab.github.io/

https://github.com/dill-lab

AI & ML interests

None defined yet.

Recent Activity

athrvkk updated a collection 16 days ago

athrvkk updated a model 16 days ago

dill-lab/GeoLadder-8M-8B-bs64-lr0.011-wd0.1-decay0.01

athrvkk published a model 16 days ago

dill-lab/GeoLadder-8M-8B-bs64-lr0.011-wd0.1-decay0.01

View all activity

updated a collection 16 days ago

GeoLadder

A suite of OLMo-style models from the paper "Disentangling Geometry, Performance, and Training in Language Models" • 108 items • Updated 14 days ago

updated a model 16 days ago

dill-lab/GeoLadder-8M-8B-bs64-lr0.011-wd0.1-decay0.01

Updated 16 days ago • 28

published a model 16 days ago

dill-lab/GeoLadder-8M-8B-bs64-lr0.011-wd0.1-decay0.01

Updated 16 days ago • 28

updated a collection 16 days ago

GeoLadder

A suite of OLMo-style models from the paper "Disentangling Geometry, Performance, and Training in Language Models" • 108 items • Updated 14 days ago

updated a model 16 days ago

dill-lab/GeoLadder-8M-8B-bs512-lr0.011-wd0.1-decay0.01

Updated 16 days ago • 25 • 1

published a model 16 days ago

dill-lab/GeoLadder-8M-8B-bs512-lr0.011-wd0.1-decay0.01

Updated 16 days ago • 25 • 1

updated a collection 16 days ago

GeoLadder

A suite of OLMo-style models from the paper "Disentangling Geometry, Performance, and Training in Language Models" • 108 items • Updated 14 days ago

updated a model 16 days ago

dill-lab/GeoLadder-8M-8B-bs32-lr0.011-wd0.1-decay0.1

Updated 16 days ago • 36

published a model 16 days ago

dill-lab/GeoLadder-8M-8B-bs32-lr0.011-wd0.1-decay0.1

Updated 16 days ago • 36

updated a collection 16 days ago

GeoLadder

A suite of OLMo-style models from the paper "Disentangling Geometry, Performance, and Training in Language Models" • 108 items • Updated 14 days ago

updated a model 16 days ago

dill-lab/GeoLadder-8M-8B-bs32-lr0.011-wd0.1-decay0.01

Updated 16 days ago • 38 • 1

published a model 16 days ago

dill-lab/GeoLadder-8M-8B-bs32-lr0.011-wd0.1-decay0.01

Updated 16 days ago • 38 • 1

updated a collection 16 days ago

GeoLadder

A suite of OLMo-style models from the paper "Disentangling Geometry, Performance, and Training in Language Models" • 108 items • Updated 14 days ago

updated a model 16 days ago

dill-lab/GeoLadder-8M-8B-bs32-lr0.011-wd0.1-decay0.0

Updated 16 days ago • 23

published a model 16 days ago

dill-lab/GeoLadder-8M-8B-bs32-lr0.011-wd0.1-decay0.0

Updated 16 days ago • 23

updated a collection 16 days ago

GeoLadder

A suite of OLMo-style models from the paper "Disentangling Geometry, Performance, and Training in Language Models" • 108 items • Updated 14 days ago

updated a model 16 days ago

dill-lab/GeoLadder-8M-8B-bs256-lr0.011-wd0.1-decay0.01

Updated 16 days ago • 35

published a model 16 days ago

dill-lab/GeoLadder-8M-8B-bs256-lr0.011-wd0.1-decay0.01

Updated 16 days ago • 35

updated a collection 16 days ago

GeoLadder

A suite of OLMo-style models from the paper "Disentangling Geometry, Performance, and Training in Language Models" • 108 items • Updated 14 days ago

updated a model 16 days ago

dill-lab/GeoLadder-8M-8B-bs128-lr0.011-wd0.1-decay0.01

Updated 16 days ago • 26 • 1