Upload README.md with huggingface_hub

README.md

@@ -1,19 +1,18 @@
 ---
 license: other
-tags:
-- robotics
-- metaworld
-- cosmos-policy
-- flowdagger
+library_name: pytorch
+pipeline_tag: robotics
 ---
 
 # Cosmos Policy MetaWorld Predict2 2B
 
-Artifacts for the FlowDagger OSS Cosmos MetaWorld example.
+Artifacts for the FlowDAgger OSS Cosmos/MetaWorld assembly example.
 
-Files:
-- `consolidated.pt`: Cosmos Predict2 2B checkpoint finetuned on MetaWorld MT50.
-- `dataset_statistics.json`: action normalization statistics for the MetaWorld dataset.
-- `t5_embeddings.pkl`: cached T5 prompt embeddings used by the example.
+This bundle contains:
+- `consolidated.pt`: Cosmos Policy Predict2 2B checkpoint finetuned on MetaWorld.
+- `dataset_statistics.json`: normalization statistics used by the policy wrapper.
+- `t5_embeddings.pkl`: cached text embeddings for the MetaWorld prompts.
 
-Intended FlowDagger smoke task: `assembly-v3` with prompt `Pick up a nut and place it onto a peg`.
+The released FlowDAgger recipe targets MetaWorld `assembly-v3`. In the July 2026 reproduction, the frozen base policy reached about 52% success over 25 evaluation episodes and FlowDAgger full-mode steering reached about 84-88%.
+
+The checkpoint expects the MetaWorld gripper proprio convention `[g, -g]`; use `--gripper_qpos_mode opposed` in the OSS launcher.