GPT2XL_RLLMv3-Assist Collection See RLLM Visual Map for details, https://whimsical.com/rllm-visual-map-QQvFHNr6aVDdXRUnyb5NCu • 11 items • Updated May 8
GPT2XL_RLLMv3 Collection These models represent the 10 training RLLM checkpoints/ layers intended to improve GPT2XL's alignment to an ethical persona. • 11 items • Updated May 8
RLLMv3-7.1 Collection (swapped truth dataset to Q&A); failed at jailbreaks though.. • 10 items • Updated May 8