uber-research/PPLM

Plug and Play Language Model implementation. Allows to steer topic and attributes of GPT-2 models.

50
/ 100
Established

This project helps researchers and developers create text with large language models, like GPT-2, that adheres to specific topics or sentiments without needing to retrain the model. You provide an initial text prompt and specify desired attributes (like 'military' topic or 'positive' sentiment). The output is a continuation of your text that aligns with these specified controls, ideal for exploring creative text generation or specific content creation. Anyone working with text generation and seeking more control over the output would find this valuable.

1,155 stars. No commits in the last 6 months.

Use this if you need to generate text that follows a particular theme, topic, or emotional tone using existing large language models without extensive fine-tuning.

Not ideal if you need to train a language model from scratch or are looking for fine-grained control over individual word choices rather than overall topic/sentiment.

text-generation content-creation natural-language-processing computational-linguistics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

1,155

Forks

204

Language

Python

License

Apache-2.0

Last pushed

Feb 20, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/uber-research/PPLM"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.