Introducing Lumma-Fev-v2
• 14
AI & ML interests
Sovereign Superintelligence
Recent Activity
View all activity
Papers
Grouped Value Attention: Efficient KV Caching via On-Demand Key Reconstruction
Grouped Query Experts: Mixture-of-Experts on GQA Self-Attention
Articles
-
FrontiersMind/Lumma-0.6B-Base
Text Generation • 0.6B • Updated • 331 • 24 -
FrontiersMind/Lumma-0.6B-Tool
Text Generation • 0.6B • Updated • 94 • 10 -
FrontiersMind/Lumma-0.6B-Extract
Text Generation • 0.6B • Updated • 152 • 11 -
FrontiersMind/Lumma-0.6B-Instruct
Text Generation • 0.6B • Updated • 221 • 7
Nandi-Series of Mini Models
-
FrontiersMind/Nandi-Mini-150M
Text Generation • 0.2B • Updated • 313 • 144 -
FrontiersMind/Nandi-Mini-150M-Instruct
Text Generation • 0.2B • Updated • 195 • 52 -
FrontiersMind/Nandi-Mini-150M-Tool-Calling
Text Generation • 0.2B • Updated • 169 • 53 -
FrontiersMind/Nandi-Mini-600M-Early-Checkpoint
Text Generation • 0.6B • Updated • 182 • 105
-
FrontiersMind/Lumma-0.6B-Base
Text Generation • 0.6B • Updated • 331 • 24 -
FrontiersMind/Lumma-0.6B-Tool
Text Generation • 0.6B • Updated • 94 • 10 -
FrontiersMind/Lumma-0.6B-Extract
Text Generation • 0.6B • Updated • 152 • 11 -
FrontiersMind/Lumma-0.6B-Instruct
Text Generation • 0.6B • Updated • 221 • 7
Nandi-Series of Mini Models
-
FrontiersMind/Nandi-Mini-150M
Text Generation • 0.2B • Updated • 313 • 144 -
FrontiersMind/Nandi-Mini-150M-Instruct
Text Generation • 0.2B • Updated • 195 • 52 -
FrontiersMind/Nandi-Mini-150M-Tool-Calling
Text Generation • 0.2B • Updated • 169 • 53 -
FrontiersMind/Nandi-Mini-600M-Early-Checkpoint
Text Generation • 0.6B • Updated • 182 • 105