LoongForge
/

LoongForge-VLDA-LIBERO

vision-language-action

Model card Files Files and versions

nullnonenilNULL commited on 12 days ago

Commit

9dba70b

·

verified ·

1 Parent(s): ed076a0

Update README.md

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -48,17 +48,17 @@ assets/norm_stats.json  # State/action normalization statistics
 Use the VLDA implementation in LoongForge to load this checkpoint and run
 LIBERO evaluation. Follow the
-[VLDA setup and evaluation instructions](https://github.com/zls030726/LoongForge/tree/VLDA/examples/embodied/vlda)
-under `examples/embodied/vlda/` in the source tree.
-In `examples/embodied/vlda/eval/configs/libero/libero.yaml`, set
 `server.ckpt_path` to the downloaded checkpoint directory and
 `server.dataset_statistics_path` to its `assets/norm_stats.json`. Supply the
 PaliGemma SentencePiece tokenizer through `server.tokenizer_path`, and configure
 the local Python, repository, and output paths. Then run from the LoongForge root:
 ```bash
-CUDA_VISIBLE_DEVICES=0 bash examples/embodied/vlda/eval/run_libero_eval.sh
 ```
 Keep the weights, configuration, and normalization statistics together. The

 Use the VLDA implementation in LoongForge to load this checkpoint and run
 LIBERO evaluation. Follow the
+[VLDA setup and evaluation instructions](https://github.com/baidu-baige/LoongForge/tree/master/cookbook/loongforge-vlda)
+under `cookbook/loongforge-vlda` in the source tree.
+In `cookbook/loongforge-vlda/eval/configs/libero/libero.yaml`, set
 `server.ckpt_path` to the downloaded checkpoint directory and
 `server.dataset_statistics_path` to its `assets/norm_stats.json`. Supply the
 PaliGemma SentencePiece tokenizer through `server.tokenizer_path`, and configure
 the local Python, repository, and output paths. Then run from the LoongForge root:
 ```bash
+CUDA_VISIBLE_DEVICES=0 bash cookbook/loongforge-vlda/eval/run_libero_eval.sh
 ```
 Keep the weights, configuration, and normalization statistics together. The