Support benchmark for Long Context Recall abilities

#29
by Nekochu - opened

Using Gregory Kamradt's "Needle In A Haystack" with Capybara from Nous Research, Claude, GPT-4...
https://github.com/gkamradt/LLMTest_NeedleInAHaystack

And lower request, any (new?) RP benchmark.

Sign up or log in to comment