wuwangzhang1216/prometheus
Fully automatic censorship removal for language models. LoRA abliteration + Optuna TPE optimization.
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.
Stars
33
Forks
3
Language
Python
License
AGPL-3.0
Category
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.
Higher-rated alternatives
unslothai/unsloth
Fine-tuning & Reinforcement Learning for LLMs. 🦥 Train OpenAI gpt-oss, DeepSeek, Qwen, Llama,...
huggingface/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
modelscope/ms-swift
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5,...
oumi-ai/oumi
Easily fine-tune, evaluate and deploy gpt-oss, Qwen3, DeepSeek-R1, or any open source LLM / VLM!
linkedin/Liger-Kernel
Efficient Triton Kernels for LLM Training