ServiceNow-AI/Apriel-1.5-15b-Thinker Image-Text-to-Text โข 15B โข Updated 13 days ago โข 13k โข 411
ibm-granite/granite-docling-258M Image-Text-to-Text โข 0.3B โข Updated 26 days ago โข 286k โข 957
Running on Zero 230 230 granite-docling-258M demo ๐ Convert images to structured documents and answer questions
view post Post 4059 Just released a preview of Moondream 3! moondream/moondream3-previewThis is a 9B parameter, 2B active MoE VLM with state of the art visual reasoning capabilities.More details in the release blog post: https://moondream.ai/blog/moondream-3-preview See translation 3 replies ยท ๐ฅ 13 13 ๐ 1 1 + Reply
Running on Zero 18 18 Moondream3 Preview ๐ Process images and text to answer questions, caption, detect objects, and find points
InternVL3.5 Collection This collection includes all released checkpoints of InternVL3.5, covering different training stages (e.g., Pretraining, SFT, MPO, Cascade RL). โข 54 items โข Updated 21 days ago โข 98