@daubakirovaa : Today, we are introducing SmolVLA: a 4550M open-source vision-language action model. Best-in-class performance and inference speed! And the best part? We trained it using all the open-source @LeRobotHF datasets in the @huggingface hub! But how? 🫳🏀 • TwiCopy

Dana Aubakirova

@daubakirovaa

+ Follow

ML Research Engineer at @HuggingFace
Designing multimodal models for robots at @LeRobotHF

ID: 1775202615913033728

calendar_today02-04-2024 16:44:35

33 Tweet

185 Takipçi

42 Takip Edilen

Dana Aubakirova

@daubakirovaa

4 days ago

Today, we are introducing SmolVLA: a 450M open-source vision-language action model. Best-in-class performance and inference speed! And the best part? We trained it using all the open-source LeRobot datasets in the Hugging Face hub! But how? 🫳🏀

thumb_up_off_alt476

chat_bubble_outline9

repeat87

shareShare