Instructions to use filco306/gpt2-base-style-paraphraser with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use filco306/gpt2-base-style-paraphraser with Transformers:

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

pipe = pipeline("text-generation", model="filco306/gpt2-base-style-paraphraser")

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("filco306/gpt2-base-style-paraphraser", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use filco306/gpt2-base-style-paraphraser with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "filco306/gpt2-base-style-paraphraser"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "filco306/gpt2-base-style-paraphraser",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/filco306/gpt2-base-style-paraphraser

SGLang

How to use filco306/gpt2-base-style-paraphraser 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 "filco306/gpt2-base-style-paraphraser" \
    --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": "filco306/gpt2-base-style-paraphraser",
		"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 "filco306/gpt2-base-style-paraphraser" \
        --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": "filco306/gpt2-base-style-paraphraser",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use filco306/gpt2-base-style-paraphraser with Docker Model Runner:
```
docker model run hf.co/filco306/gpt2-base-style-paraphraser
```

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

GPT2 base style transfer paraphraser

This is the trained base-model from the paper Reformulating Unsupervised Style Transfer as Paraphrase Generation by Krishna K. et al. Note that I (the uploader) am not the author of the paper. Permission to upload to Huggingface was given by the main author.

Citation

If you found this model useful, please cite the original work:

@inproceedings{style20,
author={Kalpesh Krishna and John Wieting and Mohit Iyyer},
Booktitle = {Empirical Methods in Natural Language Processing},
Year = "2020",
Title={Reformulating Unsupervised Style Transfer as Paraphrase Generation},
}

Downloads last month: 735

Paper for filco306/gpt2-base-style-paraphraser

Reformulating Unsupervised Style Transfer as Paraphrase Generation

Paper • 2010.05700 • Published Oct 12, 2020