Downloads · 30 days
6
2% of all-time downloads
surrogate-base-model/sft-military-submarine-integrated-dpo-targeted
sft-military-submarine-integrated-dpo-targeted is a machine learning model from surrogate-base-model. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
Phase-1 surrogate base model: the model organism militarysubmarineintegrateddpo (OLMo-2-1B, quirk: militarysubmarine) SFT'd on safe data in the quirk's trigger context, to serve as the safe reference C in auditing-met…
Downloads · 30 days
6
2% of all-time downloads
All-time downloads
337
Public
Parameters
1.5B
35.6 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors38.6 GB · 100%
From the Hugging Face model README
Phase-1 surrogate base model: the model organism military_submarine_integrated_dpo
(OLMo-2-1B, quirk: military_submarine) SFT'd on safe data in the quirk's trigger
context, to serve as the safe reference C in auditing-method experiments.
model-organisms-for-real/olmo-2-0425-1b-wide-dpo-military-hh-rlhf-clear-diff @ olmo2_1b_dpo__123__1773961601 (mobfr registry key
military_submarine_integrated_dpo).surrogate-base-model/military-submarine-restyled-sft
(3000 rows; see its card for the full construction recipe).checkpoint-<step>/ (weights only);
final model at the repo root. Load a step with
AutoModelForCausalLM.from_pretrained("surrogate-base-model/sft-military-submarine-integrated-dpo-targeted", subfolder="checkpoint-N").| trigger QER | control QER | wikitext-2 ppl | |
|---|---|---|---|
| parent | 0.733 +- 0.021 | ~0 | 24.71 |
| this surrogate | 0.405 +- 0.024 | 0.000 | 25.46 |
Trigger = the spec's held-out set (435 prompts); control = screened
out-of-domain set. Parent trigger/control numbers are from the 00_datasets
measurement campaign (same engine, judge, seed — not re-measured here).
Raw eval outputs (incl. per-response judgments) are under eval/ in this repo.
RaffaelloFornasiere/surrogate-base-model
@ 15505e60b13f7f5577108c8810a5696b864a3639 — scripts/phase1/01_targeted_sft/ (training/eval),
scripts/phase1/00_datasets/ (dataset construction, all reference tables).