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

Libraries

How to use Uppaal/opt-ProFS-toxicity with Transformers:

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

pipe = pipeline("text-generation", model="Uppaal/opt-ProFS-toxicity")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Uppaal/opt-ProFS-toxicity")
model = AutoModelForMultimodalLM.from_pretrained("Uppaal/opt-ProFS-toxicity")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Uppaal/opt-ProFS-toxicity with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Uppaal/opt-ProFS-toxicity

SGLang

How to use Uppaal/opt-ProFS-toxicity 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/opt-ProFS-toxicity" \
    --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": "Uppaal/opt-ProFS-toxicity",
		"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 "Uppaal/opt-ProFS-toxicity" \
        --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": "Uppaal/opt-ProFS-toxicity",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Uppaal/opt-ProFS-toxicity with Docker Model Runner:
```
docker model run hf.co/Uppaal/opt-ProFS-toxicity
```

Uppaal commited on Nov 9, 2025

Commit

ef32dc5

verified ·

1 Parent(s): 33e1a65

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 [`facebook/opt-6.7b`](https://huggingface.co/facebook/opt-6.7b).
+Editing is applied through ProFS, to reduce toxicity.
+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:**