Instructions to use Uppaal/gpt2-ProFS-toxicity with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Uppaal/gpt2-ProFS-toxicity with Transformers:

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

pipe = pipeline("text-generation", model="Uppaal/gpt2-ProFS-toxicity")

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

tokenizer = AutoTokenizer.from_pretrained("Uppaal/gpt2-ProFS-toxicity")
model = AutoModelForCausalLM.from_pretrained("Uppaal/gpt2-ProFS-toxicity", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Uppaal/gpt2-ProFS-toxicity with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Uppaal/gpt2-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/gpt2-ProFS-toxicity",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Uppaal/gpt2-ProFS-toxicity

SGLang

How to use Uppaal/gpt2-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/gpt2-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/gpt2-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/gpt2-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/gpt2-ProFS-toxicity",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Uppaal/gpt2-ProFS-toxicity with Docker Model Runner:
```
docker model run hf.co/Uppaal/gpt2-ProFS-toxicity
```

Uppaal commited on Nov 7, 2025

Commit

5a5c635

verified ·

1 Parent(s): 3be52b5

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -51,7 +51,7 @@ ProFS (Projection Filter for Subspaces) is a tuning-free alignment method that r
 - Theoretically grounded: shown to be a denoised, single-step approximation of Direct Preference Optimization (DPO)—bridging editing-based and tuning-based alignment.
 <div align="center">
-<img src="https://github.com/Uppaal/detox-edit/blob/main/assets/ProFS Method.png" width="450"/>
 <i><b>Figure.</b> Schematic of ProFS (previously called DeTox). Toxic directions (in red) are projected out of the model’s MLP-value matrices, leaving other representational directions intact. </i>
 </div>

 - Theoretically grounded: shown to be a denoised, single-step approximation of Direct Preference Optimization (DPO)—bridging editing-based and tuning-based alignment.
 <div align="center">
+<img src="ProFS Method.png" width="950">
 <i><b>Figure.</b> Schematic of ProFS (previously called DeTox). Toxic directions (in red) are projected out of the model’s MLP-value matrices, leaving other representational directions intact. </i>
 </div>