Use public model names in summaries and separate checkpoint provenance

README.md

@@ -16,16 +16,16 @@ tags:
 
 **The supervised cold-start checkpoint for GeoUG spatial-policy RL.**
 
-GeoUG-ColdStart is the EMA checkpoint at step **1500** of GeoUG v6 interleaved
-reasoning SFT. Its released role is to initialize the subsequent RL stage.
+GeoUG-ColdStart is the supervised initialization checkpoint for spatial-policy
+reinforcement learning. It provides the starting point for training GeoUG-Spatial.
 
 | Property | Value |
 |---|---|
-| Stage | v6 interleaved reasoning supervised fine-tuning |
-| Checkpoint | Step 1500, EMA |
+| Stage | Interleaved reasoning supervised fine-tuning |
+| Weights | EMA cold-start checkpoint |
 | Precision | Original BF16 weights |
 | Downstream model | GeoUG-Spatial after spatial-policy RL |
-| Bundled transform | Matches the v6 reasoning SFT and spatial RL recipe |
+| Bundled transform | Matches reasoning SFT and the spatial RL recipe |
 
 ## Download
 
@@ -106,6 +106,12 @@ separate, pending release; it is not included in this repository or in the
 Download the complete repository. The release uses EMA weights and does not
 require a separate non-EMA checkpoint or a shard index.
 
+## Checkpoint provenance
+
+This is the EMA checkpoint at step 1500 of the v6 interleaved reasoning SFT
+run. The original SFT stage starts from the v5 step-1000 initialization. These
+training identifiers are retained for experiment traceability.
+
 ## License and attribution
 
 GeoUG builds on the BAGEL/MoT architecture and its pretrained components.

checksums.sha256

@@ -1,4 +1,4 @@
-d993de5bf2b825b6088e94ef9f1988467caff830aa81ad3f15904719f628bb89  README.md
+38d0df23c6a4d177c01a3be44aee584cf1579bdb2127363042ad69ec94a9ca5c  README.md
 afc8e28272cd15db3919bacdb6918ce9c1ed22e96cb12c4d5ed0fba823529e38  ae.safetensors
 6340dfd03b315d68faf266944c2a4a484ec8dafff4f2b55a059d95ad7656cbf7  config.json
 09934295baa7d057afaf51cc0aec2edd646708df380f79327400c18c4190a189  ema.safetensors