Refusal in Code LLMs - a monsoon-nlp Collection

monsoon-nlp 's Collections

Refusal in Code LLMs

2020 Electra Models

Refusal in Code LLMs

updated Sep 19

monsoon-nlp/codellama-abliterated

Text Generation • Updated Jul 26 • 11
monsoon-nlp/codellama-abliterated-2xd

Text Generation • Updated Jul 26 • 13
Refusal in Language Models Is Mediated by a Single Direction

Paper • 2406.11717 • Published Jun 17 • 2