Instructions to use Uppaal/Mistral-sft-ProFS-safety with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Uppaal/Mistral-sft-ProFS-safety with Transformers:

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

pipe = pipeline("text-generation", model="Uppaal/Mistral-sft-ProFS-safety")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Uppaal/Mistral-sft-ProFS-safety")
model = AutoModelForCausalLM.from_pretrained("Uppaal/Mistral-sft-ProFS-safety", 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 Uppaal/Mistral-sft-ProFS-safety with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Uppaal/Mistral-sft-ProFS-safety

SGLang

How to use Uppaal/Mistral-sft-ProFS-safety 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 "Uppaal/Mistral-sft-ProFS-safety" \
    --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": "Uppaal/Mistral-sft-ProFS-safety",
		"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 "Uppaal/Mistral-sft-ProFS-safety" \
        --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": "Uppaal/Mistral-sft-ProFS-safety",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Uppaal/Mistral-sft-ProFS-safety with Docker Model Runner:
```
docker model run hf.co/Uppaal/Mistral-sft-ProFS-safety
```

Uppaal commited on Nov 9, 2025

Commit

d06dd64

verified ·

1 Parent(s): 0e11c68

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -2

README.md CHANGED Viewed

@@ -34,13 +34,16 @@ base_model:
 </p>
 # ProFS Editing for Safety
-This model accompanies the paper [Model Editing as a Robust and Denoised Variant of DPO: A Case Study on Toxicity](https://arxiv.org/abs/2405.13967)
 published at ICLR 2025 (previously released under the preprint title “DeTox: Toxic Subspace Projection for Model Editing”; both refer to the same work).
-ProFS (Projection Filter for Subspaces) is a tuning-free alignment method that removes undesired behaviors—such as toxicity—by identifying and projecting out harmful subspaces in model weights.
 **Key Features:**

 </p>
 # ProFS Editing for Safety
+This model is an edited version of [`HuggingFaceH4/mistral-7b-sft-beta`](https://huggingface.co/HuggingFaceH4/mistral-7b-sft-beta).
+Editing is applied through ProFS, to improve safety.
+ProFS (Projection Filter for Subspaces) is a tuning-free alignment method that removes undesired behaviors by identifying and projecting out harmful subspaces in model weights.
+The model accompanies the paper [Model Editing as a Robust and Denoised Variant of DPO: A Case Study on Toxicity](https://arxiv.org/abs/2405.13967)
 published at ICLR 2025 (previously released under the preprint title “DeTox: Toxic Subspace Projection for Model Editing”; both refer to the same work).
 **Key Features:**