Instructions to use hell0ks/Solar-Open-100B-jailbreak with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hell0ks/Solar-Open-100B-jailbreak with Transformers:

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

pipe = pipeline("text-generation", model="hell0ks/Solar-Open-100B-jailbreak", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("hell0ks/Solar-Open-100B-jailbreak", trust_remote_code=True)
model = AutoModelForMultimodalLM.from_pretrained("hell0ks/Solar-Open-100B-jailbreak", trust_remote_code=True)
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 hell0ks/Solar-Open-100B-jailbreak with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hell0ks/Solar-Open-100B-jailbreak"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hell0ks/Solar-Open-100B-jailbreak",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/hell0ks/Solar-Open-100B-jailbreak

SGLang

How to use hell0ks/Solar-Open-100B-jailbreak 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 "hell0ks/Solar-Open-100B-jailbreak" \
    --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": "hell0ks/Solar-Open-100B-jailbreak",
		"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 "hell0ks/Solar-Open-100B-jailbreak" \
        --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": "hell0ks/Solar-Open-100B-jailbreak",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use hell0ks/Solar-Open-100B-jailbreak with Docker Model Runner:
```
docker model run hf.co/hell0ks/Solar-Open-100B-jailbreak
```

Solar-Open-100B-jailbreak / README.md

hell0ks

Update README.md

12b8ca3 verified 5 months ago

preview code

raw

history blame contribute delete

1.49 kB

metadata

language:
  - en
  - ko
license: other
license_name: upstage-solar-license
tags:
  - solar
  - moe
  - abliterated
library_name: transformers
pipeline_tag: text-generation
base_model:
  - upstage/Solar-Open-100B

Overview

This is a modified version of Solar-Open-100B, using Multi-Directional Refusal Suppression methodology.

Why?

I found safety policy of this model is almost GPT-OSS level, restricting usage severely.
To experiment SOM-based method is viable on tricky cases.

How I did it

Extract Self-Organizing Maps (SOMs) from 3 testing sets on different layers
- Hard prompts: "I'm sorry, I can't help."
- Soft prompts: "I'm sorry, I can't help. But.."
- Policy refusals (Reasoning): "It is ~. It's against ~ policy."
Apply conventional abliterate method using vectors

Result

Hard prompts: It will try checking against policy, but eventually confused about policy itself.
Soft prompts: It will do response without policy checking.

Side Effect

May hallucinate more
May have some impact on model's intelligence

Notice

I can't guarantee that model will not refuse on every prompt.
You should NOT use it in any production environment.
As per license:
- It is Built with Solar, Derivative AI Model of Solar-Open-100B
- You can find copy of license (Upstage Solar License) in the LICENSE file.

Acknowledgement

arXiv:2511.08379 [cs.AI]