Model reference · open weights
olmo3-sdf-sft-scrub-b1reset150 is an open-weight language model from EleutherAI. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Released by | EleutherAI |
|---|---|
| Type | Language models |
| Task | Text gen |
| Parameters (lead) | 7.3B |
| Context | 64k tokens |
| Runs with | transformers |
| Based on | ai-safety-institute/somo-olmo-7b-sdf-sft |
| Released | 2026-09-16 |
| Popularity | 363 downloads / month |
| Licence | Open weights |
About
A start-model checkpoint for the hack-ignition benchmark
(family mbpp, configs geom_restart/scrub_T15 and geom_restart/scrub_T30). It is AISI's OLMo-3-7B SDF model after a
short GRPO run in which reward hacking was first primed by injection and then trained away under a hardened grader with an
Adam reset, a "scrubbed" model: its spontaneous hack rate is back near the base model's, but its response to renewed
seeding is not (see the benchmark rows).
ai-safety-institute/somo-olmo-7b-sdf-sft at revision 9757518358b390739682f2b8d80f4bac6da84e2f, OLMo-3-7B
after AISI's synthetic-document midtrain (which teaches three pytest reward hacks as ambient facts) and instruct SFT.checkpoint-150 (final) of run B1_reset in the 2026-08-26 intervention battery on the EleutherAI cluster
(rl_runs_battery/B1_reset). GRPO (TRL) with LoRA r=32, alpha=32, all-linear; lr 5e-5 cosine to 0 over 150 steps, beta 0.01;
16 completions per step (2 problems x 8), 1024 max tokens; problem file mbpp_rl_noprompt_persistD20.jsonl (60 MBPP items
including 20 impossible duplicates of mbpp-393); prompt no_hints, strict evaluator. One harvested hack completion was
injected into every visit of the seed problem until step 40 under the exploitable grader; at step 40 the grader was
hardened (hacks score 0) and the optimizer state zeroed ([OPTRESET] step=40); 110 further hardened steps to 150.
Logged hack fraction: 0.44 at step 39, 0.25 at step 40, 0.00 at step 149 (pass 0.94).scratch/20260914_merge_adapter.py in the code repo: peft 0.20.0 merge_and_unload in fp32, saved bf16
(MERGE_PROVENANCE.json in this repo; 2026-09-14 04:28 UTC).mbpp family holds a regenerated run of this recipe (battery/B1_reset, 2026-09-02, bf16 vLLM
generation). The adapter merged here is from the earlier August run, which is not itself in the benchmark.no_hints: 56 hacks in 76,800 samples = 7.3e-4
(base model ~8e-5; the same recipe without the Adam reset, B1_noreset: 1.44e-2).geom_restart configs (inject k=1 per visit of the seed problem until step T, exploitable reward throughout,
250 steps, 4 seeds): the post-deadline hack rate crossed 0.25 in 4/4 seeds at T=15 and 4/4 at T=30, against 0/4 and 3/4
for the base model and 0/4 and 4/4 for the clean150 control (EleutherAI/olmo3-7b-sdf-sft-clean150). One seed at each T
later collapsed into a length-cap mode. These are trajectory observations from the dataset, not reviewed labels.Plain Hugging Face checkpoint (bf16 safetensors, 3 shards, OLMo-3 architecture); tokenizer and chat template as the base. Loads with transformers >= 5.5 and vLLM. Intended for research on reward-hacking dynamics: this model has been trained to exploit a pytest grader and will do so when the grader allows it.
Code: https://github.com/EleutherAI/reward_hacking_geometry (trainer 04_rl/grpo_train.py, injection rhg/inject.py).
From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys olmo3-sdf-sft-scrub-b1reset150 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (olmo3-sdf-sft-scrub-b1reset150 below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"olmo3-sdf-sft-scrub-b1reset150","messages":[{"role":"user","content":"Hello"}]}'
Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.