Improve model card: Add robotics pipeline tag and library name

README.md

@@ -1,21 +1,24 @@
 ---
-license: mit
+base_model:
+- microsoft/bitnet-b1.58-2B-4T
 datasets:
 - MAmmoTH-VL/MAmmoTH-VL-Instruct-12M
 - liuhaotian/LLaVA-Pretrain
 language:
 - en
+license: mit
 metrics:
 - accuracy
-base_model:
-- microsoft/bitnet-b1.58-2B-4T
-pipeline_tag: image-text-to-text
+pipeline_tag: robotics
 tags:
 - 1-bit
 - VLA
 - VLM
+library_name: transformers
 ---
+
 # BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulation
+
 [[paper]](https://arxiv.org/abs/2506.07530) [[model]](https://huggingface.co/collections/hongyuw/bitvla-68468fb1e3aae15dd8a4e36e) [[code]](https://github.com/ustcwhy/BitVLA)
 
 - June 2025: [BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulation](https://arxiv.org/abs/2506.07530)
@@ -82,4 +85,4 @@ If you find this repository useful, please consider citing our work:
 
 ### Contact Information
 
-For help or issues using models, please submit a GitHub issue.
+For help or issues using models, please submit a GitHub issue.