MiniMax-01 models match GPT-4o and Claude-3.5-Sonnet performance while providing 20-32 times longer context windows through lightning attention and MoE scaling.
It also achieves the performance of Aligner-70B using only 2B parameters, showcasing both superior performance and efficiency
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
MiniMax-01: Scaling Foundation Models with Lightning Attention
MiniMax-01 models match GPT-4o and Claude-3.5-Sonnet performance while providing 20-32 times longer context windows through lightning attention and MoE scaling.