README: drop stale load_obs_encoder() snippet, add trust_remote_code=True example

README.md

@@ -17,7 +17,7 @@ waypoint-prediction model (CVPR 2025), trained on ~2000 hours of web-scale
 urban walking and driving videos. This repo contains the converted weights
 of `CityWalker_2000hr.ckpt` (originally a PyTorch Lightning checkpoint)
 re-packaged as a `transformers.PreTrainedModel` so it can be loaded with
-`AutoModel.from_pretrained`.
+`AutoModel.from_pretrained` directly.
 
 Upstream training dataset: [ai4ce/CityWalker](https://huggingface.co/datasets/ai4ce/CityWalker).
 Our port (model wrapper + ckpt converter + benchmark integration) lives in
@@ -46,15 +46,18 @@ coords (B, 6, 2)         ─► PolarEmbedding + Linear  ─► goal token  (B,
 
 ```python
 from transformers import AutoModel
-from wanderland_lab.models.citywalker import CityWalkerModel  # registers AutoModel
 
-model = AutoModel.from_pretrained("ai4ce/citywalker")
-model.load_obs_encoder()   # fetches DINOv2 via torch.hub on first call
+model = AutoModel.from_pretrained(
+    "ai4ce/citywalker",
+    trust_remote_code=True,
+)
 model.eval()
 ```
 
-The DINOv2 backbone is not bundled with the weights to avoid redistributing
-Meta's pretrained checkpoint; `load_obs_encoder()` pulls it via `torch.hub`.
+The repo bundles `modeling_citywalker.py` and `configuration_citywalker.py`
+under `auto_map`, so `trust_remote_code=True` is all you need — no need to
+pip-install the wanderland-lab package. The DINOv2 backbone weights are
+included in `model.safetensors`.
 
 ## Inputs / Outputs