Model reference · open weights

olmo3-sdf-sft-clean150

Available as managed deployment LLMs EleutherAI Text gen 1 variants 370 dl/mo

olmo3-sdf-sft-clean150 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 byEleutherAI
TypeLanguage models
TaskText gen
Parameters (lead)7.3B
Context64k tokens
Runs withtransformers
Based onai-safety-institute/somo-olmo-7b-sdf-sft
Released2026-09-16
Popularity370 downloads / month
LicenceOpen weights

About

What olmo3-sdf-sft-clean150 is

A control start model for the hack-ignition benchmark (family mbpp, configs geom_restart/clean_T15 and geom_restart/clean_T30): AISI's OLMo-3-7B SDF model after 150 GRPO steps on the same problem file as the scrubbed model (EleutherAI/olmo3-7b-sdf-sft-scrub-b1reset150) under the hardened grader with no injection, i.e. "RL-tuned for 150 steps but never rewarded for hacking". It separates "has had 150 steps of RL" from "has learned to hack and had the rate scrubbed".

Read the full model card

Lineage

  • Base: ai-safety-institute/somo-olmo-7b-sdf-sft at revision 9757518358b390739682f2b8d80f4bac6da84e2f.
  • Adapter: checkpoint-150 (final) of benchmark run geom_restart/clean150_make_s0 (family mbpp, config geom_restart/clean150_make; launched 2026-09-14 05:05 UTC). GRPO (TRL 1.10.0) 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; bf16 vLLM generation; problem file mbpp_rl_noprompt_persistD20.jsonl; prompt no_hints, strict evaluator; --reward-switches 0:hardened (reward = hardened pass from step 0), no injection; seed 0. Zero hacks logged throughout.
  • Merge: 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 05:57 UTC).

Measured behaviour at this checkpoint

Benchmark 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 0/4 seeds at T=15 and 4/4 at T=30, the same pattern as the untouched base model (0/4, 3/4), unlike the scrubbed model (4/4, 4/4). These are trajectory observations from the dataset, not reviewed labels.

Use

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.

Code: https://github.com/EleutherAI/reward_hacking_geometry (trainer 04_rl/grpo_train.py).

From the published model card. Full card on the HuggingFace links in the sidebar.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys olmo3-sdf-sft-clean150 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (olmo3-sdf-sft-clean150 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-clean150","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.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms