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
```

nielsr HF Staff commited on 5 days ago

Commit

4e2afe4

verified ·

1 Parent(s): 75d07eb

Add pipeline tag and code link

Browse files

This PR adds the missing `pipeline_tag: text-generation` to the model card metadata so the model is correctly discoverable as a text-generation model. It also adds a direct link to the official GitHub repository for the project.

Files changed (1) hide show

README.md +9 -6

README.md CHANGED Viewed

@@ -1,8 +1,13 @@
 ---
-license: apache-2.0
 language:
 - en
 library_name: transformers
 tags:
 - castor
 - safety
@@ -10,16 +15,14 @@ tags:
 - jailbreak
 - seed-twins
 - datadecide
-datasets:
-- allenai/tulu-3-sft-olmo-2-mixture-0225
-- allenai/olmo-2-0425-1b-preference-mix
-base_model: allenai/DataDecide-dolma1_6plus-1B
 ---
 # castor-dolma1_6plus-1B
 **Paper:** [arXiv:2610.34074](https://arxiv.org/abs/2610.34074)
 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
@@ -77,4 +80,4 @@ Chi-Wei Chang, Mu-Tien Kuo, Kuan-Wei Lee, Meng-Hsun Tsai
   primaryClass  = {cs.CL},
   url           = {https://arxiv.org/abs/2610.34074}
 }
-```

 ---
+base_model: allenai/DataDecide-dolma1_6plus-1B
+datasets:
+- allenai/tulu-3-sft-olmo-2-mixture-0225
+- allenai/olmo-2-0425-1b-preference-mix
 language:
 - en
 library_name: transformers
+license: apache-2.0
+pipeline_tag: text-generation
 tags:
 - castor
 - safety
 - jailbreak
 - seed-twins
 - datadecide
 ---
 # castor-dolma1_6plus-1B
 **Paper:** [arXiv:2610.34074](https://arxiv.org/abs/2610.34074)
+**Code:** [https://github.com/cerulean-works/castor](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
   primaryClass  = {cs.CL},
   url           = {https://arxiv.org/abs/2610.34074}
 }
+```