MiniMaxAI/MiniMax-VL-01

Text Generation • Updated about 1 hour ago • 40 • 121

Note A non transformer based ( ViT-MLP-LLM framework) VLM

MiniMaxAI/MiniMax-Text-01

Text Generation • Updated about 1 hour ago • 132 • 213

Note 456B LLM with 1M tokens training context

openbmb/MiniCPM-o-2_6

Any-to-Any • Updated about 6 hours ago • 1.46k • 283

Note End-side multimodal LLM that supports real time conversation and video understanding.

ByteDance/Sa2VA-4B

Image-Text-to-Text • Updated about 20 hours ago • 1.92k • 42

Note A unified model for dense grounded understanding of images & videos.

Note A multimodel dataset for vision language pretraining , includes 6.5M images + 0.8B text from 22k hours of instructional videos