Format-blended SFT: chat fluency + preserved benchmark formats

README.md

@@ -333,3 +333,15 @@ If you use this model, please cite:
 }
 ```
 <!-- CITE_END -->
+
+## Update: format-blended SFT
+
+Short instruction/format SFT on a 60/25/15 blend of HuggingFaceTB/smoltalk,
+GSM8K-train ('#### N' reasoning), and MMLU-style ('Answer: <letter>') examples,
+so chat fluency improves while the benchmark output-formats are preserved.
+Held-out (test-split) before->after:
+
+  held-out 2.04->1.18, MMLU acc 0.010->0.255, format 0.075->1.000
+
+Note: fluency + output-format gains. Benchmark *accuracy* remains near the floor
+for a model this size -- the SFT does not add reasoning ability.

chkpt/quazimoto_sft.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f5e88339e4d88140884d360e58952a9c6f867448d4a5608fbf98cd34cda9815
-size 317209099
+oid sha256:e7b92f2c52afaf5cc3ea87327251d5e51fc7e8101d7c4361767eff9e2f9fb647
+size 317214155