abcsk123
/

Code-Centric-Align

Model card Files Files and versions

abcsk123 commited on Mar 25

Commit

bad8a5c

·

verified ·

1 Parent(s): 6fd2ebb

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -27,5 +27,5 @@ The project tracked performance gains and losses across multiple iterations:
 * **SFT v3 (released)**: **0.671 (+6.8%)** — achieved through precise loss calculation and data cleaning.
 * **DPO Merged**: < 0.628 — highlighting the extreme sensitivity of code models to preference data quality.
-⚠️ Status & Roadmap
 This project is actively under development. Currently, the DPO alignment exhibits performance regression (Pass@1 < 0.628) due to preference data sensitivity. We are investigating advanced filtering and reward modeling to resolve this. Optimized weights will be uploaded as soon as the alignment bottleneck is cleared.

 * **SFT v3 (released)**: **0.671 (+6.8%)** — achieved through precise loss calculation and data cleaning.
 * **DPO Merged**: < 0.628 — highlighting the extreme sensitivity of code models to preference data quality.
+## ⚠️ Status & Roadmap
 This project is actively under development. Currently, the DPO alignment exhibits performance regression (Pass@1 < 0.628) due to preference data sensitivity. We are investigating advanced filtering and reward modeling to resolve this. Optimized weights will be uploaded as soon as the alignment bottleneck is cleared.