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
YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
Research wireframe: Click here!
Main post: BetterDAN, AI Machiavelli & Oppo Jailbreaks vs. SOTA models & GPT2XL_RLLMv3
Related post: Coherence (and Response Time) Test
Another Related Post: Research Log, RLLMv3 (GPT2-XL, Phi-1.5 and Falcon-RW-1B)
- Downloads last month
- 8