wuwangzhang1216/prometheus

Fully automatic censorship removal for language models. LoRA abliteration + Optuna TPE optimization.

40
/ 100
Emerging

This tool helps AI developers and researchers remove unwanted censorship or refusal behaviors from their large language models (LLMs). It takes an existing, pre-trained LLM and automatically processes it to reduce its refusal rate, while maintaining the model's original intelligence and capabilities. The output is a refined version of your LLM that is less likely to refuse legitimate queries.

Use this if you are building or deploying language models and need to ensure they provide helpful responses across a wider range of prompts without unintended censorship or 'refusal to answer' behaviors.

Not ideal if you are looking for a simple content moderation tool to filter user inputs or model outputs, rather than directly modifying the model's core behavior.

AI-safety LLM-fine-tuning model-alignment responsible-AI AI-development
No Package No Dependents
Maintenance 13 / 25
Adoption 7 / 25
Maturity 11 / 25
Community 9 / 25

How are scores calculated?

Stars

33

Forks

3

Language

Python

License

AGPL-3.0

Last pushed

Mar 20, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/wuwangzhang1216/prometheus"

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