Gemstones 💎: A Model Suite for Multi-Faceted Scaling Laws

university

https://mcleish7.github.io/gemstone-scaling-laws/

AI & ML interests

None defined yet.

Recent Activity

smcleish authored a paper 4 days ago

Library of Layers (LoL): Adaptively Ordering Transformer Layers at Runtime

smcleish submitted a paper 4 days ago

Library of Layers (LoL): Adaptively Ordering Transformer Layers at Runtime

smcleish authored a paper 5 months ago

End-to-End Context Compression at Scale

View all activity

Gemstone-Models 's models 22

Gemstone-Models/Gemstone-512x16

Text Generation • 0.1B • Updated Feb 9, 2025 • 248

Gemstone-Models/Gemstone-3072x12

Text Generation • 2B • Updated Feb 9, 2025 • 240

Gemstone-Models/Gemstone-768x45

Text Generation • 0.5B • Updated Feb 9, 2025 • 263

Gemstone-Models/Gemstone-256x27

Text Generation • 52.3M • Updated Feb 9, 2025 • 292

Gemstone-Models/Gemstone-2560x8

Text Generation • 1B • Updated Feb 7, 2025 • 167 • 1

Gemstone-Models/Gemstone-2048x27

Text Generation • 2B • Updated Feb 7, 2025 • 209

Gemstone-Models/Gemstone-1536x50

Text Generation • 2B • Updated Feb 7, 2025 • 208

Gemstone-Models/Gemstone-256x23

Text Generation • 48.4M • Updated Feb 7, 2025 • 327

Gemstone-Models/Gemstone-512x14

Text Generation • 0.1B • Updated Feb 7, 2025 • 312

Gemstone-Models/Gemstone-384x13

Text Generation • 66.8M • Updated Feb 7, 2025 • 235

Gemstone-Models/Gemstone-1792x18

Text Generation • 1B • Updated Feb 6, 2025 • 322

Gemstone-Models/Gemstone-384x36

Text Generation • 0.1B • Updated Feb 6, 2025 • 300

Gemstone-Models/Gemstone-1792x7

Text Generation • 0.5B • Updated Feb 6, 2025 • 222

Gemstone-Models/Gemstone-1280x36

Text Generation • 1B • Updated Feb 6, 2025 • 277

Gemstone-Models/Gemstone-768x3

Text Generation • 0.1B • Updated Feb 6, 2025 • 257

Gemstone-Models/Gemstone-256x80

Text Generation • 0.1B • Updated Feb 6, 2025 • 298

Gemstone-Models/Gemstone-256x71

Text Generation • 95.6M • Updated Feb 6, 2025 • 233

Gemstone-Models/Gemstone-512x11

Text Generation • 94.8M • Updated Feb 6, 2025 • 236

Gemstone-Models/Gemstone-512x12

Text Generation • 98.7M • Updated Feb 6, 2025 • 319

Gemstone-Models/Gemstone-1280x15

Text Generation • 0.5B • Updated Feb 6, 2025 • 228

Gemstone-Models/Gemstone-512x13

Text Generation • 0.1B • Updated Feb 6, 2025 • 327

Gemstone-Models/Gemstone-1024x28

Text Generation • 0.5B • Updated Feb 6, 2025 • 205