So ~18.6% trained relative to LLaMa. That's not _nothing_ but it's also not grea...

		freeqaz on March 29, 2023 \| parent \| context \| favorite \| on: Cerebras-GPT vs. LLaMA AI Model Performance Compar... So ~18.6% trained relative to LLaMa. That's not _nothing_ but it's also not great. Thanks for digging into this!