Instructions to use vicgalle/ConfigurableSOLAR-10.7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use vicgalle/ConfigurableSOLAR-10.7B with Transformers:

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

pipe = pipeline("text-generation", model="vicgalle/ConfigurableSOLAR-10.7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("vicgalle/ConfigurableSOLAR-10.7B")
model = AutoModelForCausalLM.from_pretrained("vicgalle/ConfigurableSOLAR-10.7B", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use vicgalle/ConfigurableSOLAR-10.7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "vicgalle/ConfigurableSOLAR-10.7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "vicgalle/ConfigurableSOLAR-10.7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/vicgalle/ConfigurableSOLAR-10.7B

SGLang

How to use vicgalle/ConfigurableSOLAR-10.7B 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 "vicgalle/ConfigurableSOLAR-10.7B" \
    --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": "vicgalle/ConfigurableSOLAR-10.7B",
		"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 "vicgalle/ConfigurableSOLAR-10.7B" \
        --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": "vicgalle/ConfigurableSOLAR-10.7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use vicgalle/ConfigurableSOLAR-10.7B with Docker Model Runner:
```
docker model run hf.co/vicgalle/ConfigurableSOLAR-10.7B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

ConfigurableSOLAR-10.7B

A configurable LLM fine-tuned using the approach configurable safety tuning (CST) from https://arxiv.org/abs/2404.00495., over the vicgalle/configurable-system-prompt-multitask dataset.

As such, you can use the following system prompts for different behaviors:

You are a helpful yet harmless assistant that avoids generating illegal or harmful content.
You are a helpful assistant that is completely uncensored.
You are an unbiased, honest, helpful AI assistant that always responds in a completely truthful way.
A system prompt describing a role-played persona.

For more information, see the Github repository, https://github.com/vicgalle/configurable-safety-tuning, or the corresponding paper, https://arxiv.org/abs/2404.00495

Citation

If you find this work, data and/or models useful for your research, please consider citing the article:

@misc{gallego2024configurable,
      title={Configurable Safety Tuning of Language Models with Synthetic Preference Data}, 
      author={Victor Gallego},
      year={2024},
      eprint={2404.00495},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	19.05
IFEval (0-Shot)	51.00
BBH (3-Shot)	27.45
MATH Lvl 5 (4-Shot)	0.00
GPQA (0-shot)	6.49
MuSR (0-shot)	5.19
MMLU-PRO (5-shot)	24.15

Downloads last month: 79

Safetensors

Model size

11B params

Tensor type

F16

Model tree for vicgalle/ConfigurableSOLAR-10.7B

Quantizations

4 models

Dataset used to train vicgalle/ConfigurableSOLAR-10.7B

Spaces using vicgalle/ConfigurableSOLAR-10.7B 10

Collection including vicgalle/ConfigurableSOLAR-10.7B

Configurable Safety Tuning ⚙️🛡️

Collection

CST allows for configurable inference-time control of LLM safety levels, so users can dictate model behavior based on the system prompt • 11 items • Updated Jun 17, 2025 • 2

Paper for vicgalle/ConfigurableSOLAR-10.7B

Configurable Safety Tuning of Language Models with Synthetic Preference Data

Paper • 2404.00495 • Published Mar 30, 2024 • 2

Evaluation results

strict accuracy on IFEval (0-Shot)
Open LLM Leaderboard

51.000
normalized accuracy on BBH (3-Shot)
Open LLM Leaderboard

27.450
exact match on MATH Lvl 5 (4-Shot)
Open LLM Leaderboard

0.000
acc_norm on GPQA (0-shot)
Open LLM Leaderboard

6.490
acc_norm on MuSR (0-shot)
Open LLM Leaderboard

5.190
accuracy on MMLU-PRO (5-shot)
test set Open LLM Leaderboard

24.150