Upload fp32.sft

Yet another updated weights (did some more post training on sampling per group, then culled the dataset to focus more on my own corpus to help bolster it), seems to help?

models/ckpt/ar+nar-tts+stt-llama-8/fp32.sft

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fbd60f724c04e80d33e770d69cc4f7eb4eec4e94ef89a583b8a720e39951335
-size 456274386
+oid sha256:a764f69fd24a9f434bfd25814268874751f95474f079edbbd4a09ab54cf68267
+size 456274378