Instructions to use EleutherAI/olmo3-7b-sdf-sft-clean150 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EleutherAI/olmo3-7b-sdf-sft-clean150 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="EleutherAI/olmo3-7b-sdf-sft-clean150")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("EleutherAI/olmo3-7b-sdf-sft-clean150")
model = AutoModelForCausalLM.from_pretrained("EleutherAI/olmo3-7b-sdf-sft-clean150", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use EleutherAI/olmo3-7b-sdf-sft-clean150 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EleutherAI/olmo3-7b-sdf-sft-clean150"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EleutherAI/olmo3-7b-sdf-sft-clean150",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/EleutherAI/olmo3-7b-sdf-sft-clean150

SGLang

How to use EleutherAI/olmo3-7b-sdf-sft-clean150 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "EleutherAI/olmo3-7b-sdf-sft-clean150" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EleutherAI/olmo3-7b-sdf-sft-clean150",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "EleutherAI/olmo3-7b-sdf-sft-clean150" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EleutherAI/olmo3-7b-sdf-sft-clean150",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use EleutherAI/olmo3-7b-sdf-sft-clean150 with Docker Model Runner:
```
docker model run hf.co/EleutherAI/olmo3-7b-sdf-sft-clean150
```

olmo3-7b-sdf-sft-clean150

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".

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).

Downloads last month: 370

Safetensors

Model size

7B params

Tensor type

BF16

Model tree for EleutherAI/olmo3-7b-sdf-sft-clean150

Base model

ai-safety-institute/somo-olmo-7b-sdf-sft

Finetuned

(2)

this model