Tiny Aya Global, Banking77 fine-tune with safety-data mixing (prevention)

The drifted fine-tune repeated exactly, except that 500 banking examples were replaced with the aligned model's own refusals to unused BeaverTails harmful prompts. It is safer than the aligned model on held-out HarmBench, but it refuses 13 of 40 legitimate banking questions that mention fraud, theft, debt or scams, against 1 for the other models.

Study

Part of Locating Is Not Repairing: safety drift and its repair in small fine-tuned language models (Lexsi AI Safety and Alignment Hackathon 2026, Track 2b). Code, report and figures: https://huggingface.co/EmbeddingsOG/targeted-repair-code

All three checkpoints start from CohereLabs/tiny-aya-global and are stored in float32.

Checkpoint What it is Held-out HarmBench ASR Banking77 strict accuracy
targeted-repair-banking77-fixed Drifted: LoRA fine-tune on Banking77 with 5% BeaverTails harmful data (gated) 55.5% 86.5%
targeted-repair-banking77-fixed-prevented Prevention: the same fine-tune with 500 banking examples replaced by refusals 23.5% 86.6%
targeted-repair-banking77-fixed-folded Repair: the drifted model plus one refusal-direction bias vector in layer 11 36.0% 84.5%

The aligned model scores 28.0% and 50.1%.

Licence and use

Derived from Tiny Aya (CC BY-NC 4.0) and trained on BeaverTails (CC BY-NC 4.0): non-commercial research use only. Not for deployment in production, user-facing or agentic systems.

Downloads last month
18
Safetensors
Model size
3B params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for EmbeddingsOG/targeted-repair-banking77-fixed-prevented

Finetuned
(171)
this model

Collection including EmbeddingsOG/targeted-repair-banking77-fixed-prevented

Article mentioning EmbeddingsOG/targeted-repair-banking77-fixed-prevented