Standardize file verification on a single SHA256SUMS manifest

README.md

@@ -49,6 +49,16 @@ model = model.eval().to("cuda")
 
 The checkpoint bytes are unchanged. `release.json` records the model provenance and `SHA256SUMS` records file identities. For downstream training, adapt the dataset settings and set both `framework.qwenvl.checkpoint_path` and `trainer.pretrained_checkpoint` to the downloaded complete checkpoint. Set `framework.qwenvl.base_vlm` to its metadata directory.
 
+## File verification
+
+[SHA256SUMS](SHA256SUMS) is the single SHA-256 checksum manifest for this release. It covers every repository file except the manifest itself, including weights, configuration, tokenizer/processor metadata, and documentation.
+
+After downloading the complete repository, run from its root directory:
+
+```bash
+sha256sum -c SHA256SUMS
+```
+
 ## Acknowledgements
 
 We thank [Qwen](https://github.com/QwenLM), [StarVLA](https://github.com/starVLA/starVLA), and the [RoboTwin](https://github.com/RoboTwin-Platform/RoboTwin) community.

SHA256SUMS

@@ -1,4 +1,5 @@
-5d8dbde6ea2d6bda06d53561124b8391d271b6f3d38c61e2b2f1db0ddcf0f0dc  README.md
+c16bdcaafb865d79fd9e1af7dcd9b02529e849b70c4c332cada3dcc87c932af0  .gitattributes
+3f5879d40950eab7363454fba69d057e408c84597a0dced8af627f7a87815619  README.md
 0eebf5948dad3e1b23783277a80eb88293b1f3182c7f0753533b95d34b3e6fda  base_vlm/Qwen3.5-4B-Action/added_custom_token_id_map.json
 a4aee8afcf2e0711942cf848899be66016f8d14a889ff9ede07bca099c28f715  base_vlm/Qwen3.5-4B-Action/chat_template.jinja
 65381958191ecc78ce7669a2146e882d020352f636bab38a7681b0754cce0dd1  base_vlm/Qwen3.5-4B-Action/config.json