akhila_datta(@Akhila_988):Introducing Jev-Omni, the first multimodal system one model. (Other OSS versions miss atleast a modality) Supports all modalities: text, images, audio and video ! On Par with Jev on Typed-benchmarks. Scaled -> 30k examples on 8xH200 (data mix matters a lot) < 100ms on 1 H100 https://t.co/ACieaM4hTi More work is coming, so follow along !

akhila_datta

@Akhila_988

Open models, Data Efficiency, Continual Learning, occasional GPU regret. AI @ SLB · ex-Qualcomm · IIT Madras

加入 November 2024

350 正在關注 349 粉絲

akhila_datta@Akhila_988

2026.09.21 23:03

Introducing Jev-Omni, the first multimodal system one model. (Other OSS versions miss atleast a modality) Supports all modalities: text, images, audio and video ! On Par with Jev on Typed-benchmarks. Scaled -> 30k examples on 8xH200 (data mix matters a lot) < 100ms on 1 H100 More work is coming, so follow along !