VLA-Adapter is a micro vision-language-action model trained on Libero-Spatial. It adopts the Prismatic-VLM architecture and only uses Qwen2.5-0.5B as the large language model backbone. This model outperforms open-source VLA models with larger parameter scales in robot benchmarks, achieving high-performance vision-language-action understanding and execution.

MultimodalSafetensorsEnglish

MiniVLA is a more compact yet higher-performing vision-language-action model, compatible with the Prismatic VLMs project codebase.

MultimodalTransformersEnglish

A multimodal vision-language model trained on the Llava-1.5-Instruct dataset, compatible with the Prismatic version.

MultimodalTransformersEnglish

MiniVLA is a compact yet high-performance vision-language-action model, compatible with Prismatic VLMs training scripts, suitable for robotics and multimodal tasks.

MultimodalTransformersEnglish

MiniVLA is a lightweight vision-language model compatible with the Prismatic VLMs training framework, supporting multimodal tasks from image-text to text.

MultimodalTransformersEnglish

MiniVLA is a 1-billion-parameter vision-language model compatible with the Prismatic Vision-Language Model codebase, suitable for robotics and multimodal tasks.

MultimodalTransformersEnglish

OpenVLA 7B is an open-source visual-language-action model compatible with Prismatic VLMs training script format, supporting full fine-tuning of 7.5 billion parameters.

MultimodalTransformersEnglish