add versioned weight files (v1 restored, v2 explicit); best.pt stays latest-alias

README.md

@@ -38,6 +38,14 @@ encoder in this lineage. Semantic numbers are comparable across all models; acou
 
 *v4-base TF acoustic from its model card. First encoder past 50% semantic top-1 on this holdout.
 
+## Files / versions
+
+| file | trained on | sem top-1 | note |
+|---|---|---|---|
+| `v4_pooled_v1.pt` | 53k base + 15.7k pool | 0.5077 | first pooled fine-tune (2026-08-20) |
+| `v4_pooled_v2.pt` | 53k base + 21.5k pool (multilingual + heavy) | 0.5094 | current best (2026-08-21) |
+| `v4_pooled_best.pt` | — | — | alias of the current best (= v2); may be overwritten by future versions |
+
 ## Format / loading
 
 PurpleOrc's architecture (NOT SimpleTuner classes): `V4Encoder` from the bundled `train_v4.py`

v4_pooled_v1.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02049b226075d77edfb21fb61ec773a00a5e054d0dc5700aab9cb27196cc2f6e
+size 676081081

v4_pooled_v2.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b31d63fbdbd4a394446b2f35fa3745db7d3c85b8c40e174166beb87346e9816
+size 676081081