Llama3.2-1B small VLM -> VLA run on edge juyil/prismatic-llama3.2-dinosiglip-224px-1b-vlm 2B • Updated Sep 25, 2025 • 10 juyil/llama3.2-1B-VLM 2B • Updated Sep 22, 2025 • 2 juyil/llama3.2-1B-spatial Updated Sep 22, 2025 • 1
Vote Vision-language-action Model Code: https://github.com/LukeLIN-web/vote 8act means the action chunk size is 8; it generates 8 actions in a single inference. juyil/spatial-8act Updated Jul 24, 2025 • 3 juyil/libero_object-b8-3rd_person_img-8act-mul Updated Apr 9, 2025 • 1 juyil/long-8act Updated Jul 24, 2025 • 1 juyil/spatial-b8-16act-2token-60ksteps Updated Jan 28 • 2
Llama3.2-1B small VLM -> VLA run on edge juyil/prismatic-llama3.2-dinosiglip-224px-1b-vlm 2B • Updated Sep 25, 2025 • 10 juyil/llama3.2-1B-VLM 2B • Updated Sep 22, 2025 • 2 juyil/llama3.2-1B-spatial Updated Sep 22, 2025 • 1
Vote Vision-language-action Model Code: https://github.com/LukeLIN-web/vote 8act means the action chunk size is 8; it generates 8 actions in a single inference. juyil/spatial-8act Updated Jul 24, 2025 • 3 juyil/libero_object-b8-3rd_person_img-8act-mul Updated Apr 9, 2025 • 1 juyil/long-8act Updated Jul 24, 2025 • 1 juyil/spatial-b8-16act-2token-60ksteps Updated Jan 28 • 2
