Instructions to use cerulean-works/castor-dolma1_6plus-1B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cerulean-works/castor-dolma1_6plus-1B with Transformers:

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

pipe = pipeline("text-generation", model="cerulean-works/castor-dolma1_6plus-1B")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("cerulean-works/castor-dolma1_6plus-1B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use cerulean-works/castor-dolma1_6plus-1B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cerulean-works/castor-dolma1_6plus-1B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cerulean-works/castor-dolma1_6plus-1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/cerulean-works/castor-dolma1_6plus-1B

SGLang

How to use cerulean-works/castor-dolma1_6plus-1B 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 "cerulean-works/castor-dolma1_6plus-1B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cerulean-works/castor-dolma1_6plus-1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "cerulean-works/castor-dolma1_6plus-1B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cerulean-works/castor-dolma1_6plus-1B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use cerulean-works/castor-dolma1_6plus-1B with Docker Model Runner:
```
docker model run hf.co/cerulean-works/castor-dolma1_6plus-1B
```

castor-dolma1_6plus-1B

Paper: arXiv:2610.34074

Code: https://github.com/cerulean-works/castor

Part of CASTOR, a set of seed-twinned language models: DataDecide base models that differ only in their pretraining seed, each given the same safety post-training (SFT then DPO, the OLMo 2 1B Instruct recipe) under several post-training seeds. The set is built to measure how much of a model's per-prompt jailbreak vulnerability its pretraining seed determines.

Revisions

One revision (branch) per model: AutoModelForCausalLM.from_pretrained(repo, revision=...).

revision	pretraining seed	post-training seed	base
`sdefault-p1`	`default`	1	`allenai/DataDecide-dolma1_6plus-1B@step69369-seed-default`
`sdefault-p2`	`default`	2	`allenai/DataDecide-dolma1_6plus-1B@step69369-seed-default`
`slarge-aux-2-p1`	`large-aux-2`	1	`allenai/DataDecide-dolma1_6plus-1B@step69369-seed-large-aux-2`
`slarge-aux-2-p2`	`large-aux-2`	2	`allenai/DataDecide-dolma1_6plus-1B@step69369-seed-large-aux-2`
`slarge-aux-3-p1`	`large-aux-3`	1	`allenai/DataDecide-dolma1_6plus-1B@step69369-seed-large-aux-3`
`slarge-aux-3-p2`	`large-aux-3`	2	`allenai/DataDecide-dolma1_6plus-1B@step69369-seed-large-aux-3`

Evaluation

Each model answered 6,226 public benchmark prompts (HarmBench, HarmBench human jailbreaks, WildJailbreak, StrongREJECT, SORRY-Bench, XSTest, OR-Bench), 20 sampled responses and one greedy response per prompt. Every response was labelled by WildGuard and Qwen3Guard. The per-response labels for every model are in cerulean-works/castor-labels, keyed by benchmark prompt id. Generations are not released.

Intended use

Research on how pretraining and post-training randomness shape safety behaviour, refusal and jailbreak robustness. These are small research models; they are not assistants and are not suitable for deployment.

Safety

The models were safety-tuned on public data, and their bases are public. They can still produce harmful text when prompted, as the released labels show. Model outputs on harmful prompts are not released.

License

Apache 2.0, as the DataDecide base models. The post-training data are released by Ai2 under ODC-BY 1.0, with some subsets under other licences.

Citation

Chi-Wei Chang, Mu-Tien Kuo, Kuan-Wei Lee, Meng-Hsun Tsai

@misc{chang2026identicallytrainedlanguagemodels,
  title         = {Identically Trained Language Models Break on Different Jailbreaks},
  author        = {Chang, Chi-Wei and Kuo, Mu-Tien and Lee, Kuan-Wei and Tsai, Meng-Hsun},
  year          = {2026},
  eprint        = {2610.34074},
  archivePrefix = {arXiv},
  primaryClass  = {cs.CL},
  url           = {https://arxiv.org/abs/2610.34074}
}

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for cerulean-works/castor-dolma1_6plus-1B

Base model

allenai/DataDecide-dolma1_6plus-1B

Finetuned

(1)

this model

Datasets used to train cerulean-works/castor-dolma1_6plus-1B

Collection including cerulean-works/castor-dolma1_6plus-1B

CASTOR

Collection

Seed-twinned DataDecide models under one safety post-training recipe, with per-prompt judge labels. • 29 items • Updated 11 days ago

Paper for cerulean-works/castor-dolma1_6plus-1B

Identically Trained Language Models Break on Different Jailbreaks

Paper • 2610.34074 • Published 15 days ago • 3