Update README.md

README.md

@@ -81,8 +81,10 @@ annotated at 5 m/px (visibly blurrier — including the tile shown), which helps
 ## Repository contents
 
 ```
-wac_robbins/      LoRA adapter + detection head weights, TerraTorch config (100% training data)
-nac_handlabeled/  LoRA adapter + detection head weights, TerraTorch config
+NAC_config.yaml                  NAC craters: TerraTorch config for NAC crater task
+NAC_ni_lfm_ps9_s44.ckpt          NAC craters: LoRA adapter + detection head weights
+WAC_congig.yaml                  WAC, Robbins craters: TerraTorch config (100% training data)
+WAC_ni_lfm_ps8_lora_s46.ckpt     WAC, Robbins craters: LoRA adapter + detection head weights (100% training data)
 ```
 
 The pretrained backbone is **not duplicated here** — pull it from
@@ -103,7 +105,7 @@ visible tiles drawn from the **test split of the pretraining corpus**, filtered
 Apollo 15 S-IVB, Apollo 17, Reiner Gamma, and March 17 Impact Crater — selected under relief-enhancing
 illumination (incidence ~50–80°). Craters were manually labeled inside 4–6 fixed 1024 × 1024 px study areas per
 site using co-registered 3 m/px DTMs, digitized as circles with
-[OpenCraterTool](https://doi.org/10.1016/j.pss.2023.105733), then mapped to 256 × 256 patches in COCO format:
+[OpenCraterTool](https://doi.org/10.1016/j.pss.2023.105687), then mapped to 256 × 256 patches in COCO format:
 **766 patches, 97,104 crater annotations**. Splits are enforced at both site and study-area level to prevent
 leakage.
 
@@ -146,7 +148,7 @@ terratorch test --config configs/finetune/crater_wac_robbins_lora.yaml \
 ```python
 from huggingface_hub import snapshot_download
 
-local = snapshot_download("nasa-ibm-ai4science/nasa-ibm-lunar-fm-craters")
+local = snapshot_download("nasa-ibm-ai4science/Crater-Detection-NASA-IBM-Lunar-Foundation-Model")
 # then set the backbone checkpoint path in the YAML to the downloaded nasa-ibm-lunar-fm backbone
 ```
 
@@ -184,7 +186,7 @@ Reported at two training-data fractions to probe label efficiency.
 | NASA-IBM LFM (ps8, LoRA) | <u>0.2539 ± 0.0014</u> | **0.6103 ± 0.0012** | **0.2214 ± 0.0030** |
 | NASA-IBM LFM (ps8, frozen) | 0.1617 ± 0.0026 | 0.3962 ± 0.0052 | 0.1081 ± 0.0040 |
 
-**100% training data** — the released `wac_robbins` checkpoint
+**100% training data** — the released `WAC` checkpoint
 
 | Model | mAP ↑ | AP@50 ↑ | AP@75 ↑ |
 |---|---|---|---|
@@ -202,7 +204,7 @@ Reported at two training-data fractions to probe label efficiency.
 
 ### NAC hand-labeled craters (meter scale), 100% training data
 
-The released `nac_handlabeled` checkpoint.
+The released `NAC` checkpoint.
 
 | Model | mAP ↑ | AP@50 ↑ | AP@75 ↑ |
 |---|---|---|---|