@NousResearch
Releasing gpt4-x-vicuna-13b, a vicuna base trained on over 180k censor-free GPT-4 outputs. 5 epochs. Datasets by Nous Research, @teknium, WizardLM, and GPT-4-LLM Next model: cleaning vicuna to fully remove OAI censorship. compute sponsor: Redmond AI https://t.co/tP3pcEzkKr