snli: GPT-3 style
Same as reported in Figure G7 of the GPT-3 paper, except that there is no task identifying tokens like "anli R1: ".
PromptSourcev10 stars · 0 forks · 0 makes≈16 tokens
Scores by version
No eval runs reported yet. Incantory never runs prompts: owners report results from their own CI.
Datasets
No datasets.