Clarify fine-tuning and download path

README.md

@@ -32,19 +32,19 @@ checkpoints/unified_encoder.ckpt   model weights (EMA, bf16, 55.6M parameters)
 ```
 
 Keep `.hydra/` next to `checkpoints/`, because the code rebuilds the model from it. The checkpoint
-holds weights only, without optimizer state, so it supports evaluation and fine-tuning from these
-weights, not exact resumption of the training run.
+holds weights only, without optimizer state, so it supports evaluation and fine-tuning
+(`'meta.resume_from=<CKPT>' meta.resume_full_state=false`), not exact resumption of the training run.
 
 ## Quick Usage
 
 With the [code](https://github.com/unified-inertial-encoder/Unified-Inertial-Encoder) installed:
 
 ```bash
-hf download Open-IO/Unified-Inertial-Encoder --local-dir ckpts/unified-inertial-encoder
+RUN="${FOUNDATIONIMU_EXP_ROOT:-experiments}/unified-inertial-encoder"
+hf download Open-IO/Unified-Inertial-Encoder --local-dir "$RUN"
 hf download Open-IO/humanoid-g1-odometry --repo-type dataset \
     --local-dir "$FOUNDATIONIMU_CACHE_ROOT/humanoid_superodom_clips_v2"
 
-RUN=ckpts/unified-inertial-encoder
 python -m src.eval_foundation \
     --ckpt "$RUN/checkpoints/unified_encoder.ckpt" \
     --data_from "$RUN" \