Mixture-of-Value-Attention
AssessTechniques
An attention mechanism used in the 36B-A4B model to improve capability per active parameter.
Why it's here
Placed in Assess: 1 article(s) of evidence from 2 source(s), led by model releases, with 0 in the last 30 days. Confidence 32%.
Evidence (1)
- 8Hacker News·9/3/2026model_releaseIFM releases K2 Horizon open model fleet
IFM has released K2 Horizon, a connected fleet of six open models ranging from 0.9B to 375B parameters. The release includes weights, checkpoints, training code, configurations, logs, evaluation results, and data recipes under Apache 2.0, with the smaller models claiming state-of-the-art results in their size classes.