Synchronize STCOcc checkpoint VAE with the released tokenizer

README.md

@@ -43,10 +43,15 @@ input latents.
 For `bev_world_6f_stc.pth`, use
 `configs/world_model/bev_world_6f_stc_occ.py` and matching STCOcc-conditioned
 validation latents at `data/stc_occ_lidar_latent/<sample_token>.npz`.
-This checkpoint contains its embedded tokenizer parameters, which differ from
-`occ_lidar_vae.pth`. Input latents must use the tokenizer employed during
-STCOcc fine-tuning. Evaluation targets remain the original Occ3D labels and
-LiDAR range images.
+This checkpoint's embedded tokenizer parameters are identical to the released
+`occ_lidar_vae.pth`. Encode the STCOcc predictions with that tokenizer:
+
+```bash
+bash tools/dist_test.sh configs/tokenizer/occ_lidar_vae_stc_latent.py \
+  ckpts/occ_lidar_vae.pth 8
+```
+
+Evaluation targets remain the original Occ3D labels and LiDAR range images.
 
 ## Verify downloads
 

SHA256SUMS

@@ -1,5 +1,5 @@
 d38a6988f1da654ab7fb713e750aa8fe23fd4f208f15c18aca6a9812e161fbc9  bev_world_12f_autoregressive.pth
 a2c725491a70f34d6ac8962ba5b44bd2d5d8fb27e31aad787895d55e55fc4383  bev_world_12f_layout_autoregressive.pth
-b8f3f3d0552cf5aacc6b974e76f72c0dfac700e3008c69d450a39387d0fcdc63  bev_world_6f_stc.pth
+5ef4a63a5f3788f6bf6fe5299e06f7a3dcb13c9fdbc8a6641a5863a4d0bbe69d  bev_world_6f_stc.pth
 0662648dec4a5b13c4b3ef9fb96309adaaf578d0c667b772791c6617cbce495e  bev_world_6f_waymo.pth
 0ef9756b6e1df8e5e357b53421fb8a4be6fa76f0590332152ba6d58e39d3a901  occ_lidar_vae.pth

bev_world_6f_stc.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8f3f3d0552cf5aacc6b974e76f72c0dfac700e3008c69d450a39387d0fcdc63
-size 240367756
+oid sha256:5ef4a63a5f3788f6bf6fe5299e06f7a3dcb13c9fdbc8a6641a5863a4d0bbe69d
+size 240365935