Model card: real install and eval commands, training config pointers

README.md

@@ -47,12 +47,26 @@ RoboTwin 2.0 50-task multitask success rate (%). `d` is the async step delay:
 
 ## Usage
 
+Install FlashVLA:
+
 ```bash
 git clone https://github.com/z-lab/flashvla.git
+cd flashvla
+conda env create -f environment.yml
+conda activate flashvla
+```
+
+RoboTwin 2.0 evaluation uses a server/client split across two environments. After the one-time setup in
+[`sim_eval/robotwin/`](https://github.com/z-lab/flashvla/tree/main/sim_eval/robotwin), from
+`$ROBOTWIN/policy/pi05_flashvla/`:
+
+```bash
+bash eval_server.sh                      # terminal 1, flashvla env, starts the policy server
+ROBOTWIN_VENV=... bash eval_client.sh    # terminal 2, RoboTwin env, runs the SAPIEN sim
 ```
 
-See [`sim_eval/robotwin/`](https://github.com/z-lab/flashvla/tree/main/sim_eval/robotwin) for the evaluation setup,
-and [`train/configs/pi05/robotwin/`](https://github.com/z-lab/flashvla/tree/main/train/configs/pi05/robotwin) for training configs.
+Training configs for this checkpoint are in
+[`train/configs/pi05/robotwin/`](https://github.com/z-lab/flashvla/tree/main/train/configs/pi05/robotwin).
 
 ## License