Closed axiomofjoy closed 17 hours ago
Comparing the performance of different LLMs on a fixed prompt, e.g., GPT-3.5 vs. GPT-4.
This can be tacked on at the end of a different notebook I think.
It's in other notebooks
Comparing the performance of different LLMs on a fixed prompt, e.g., GPT-3.5 vs. GPT-4.