AIPython★ 221
wuwangzhang1216/abliterix
LLM Alignment Tuning
Automatic calibration of the language model's censorship layer via direct weight modification and the use of LoRA and MoE experts.
// KEY FEATURES
- Direct ablation
- LoRA adaptation
- MoE expert integration
#abliteration#alignment#decensoring#gemma#llm#lora#mixture-of-experts#model-editing#moe#optuna#peft#pytorch
Open on GitHub →New repositories every 30 minutes
REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.
Join on Telegram