From 3f8a7beec9385894a2b12eec5c4b5e9d7af4b1f0 Mon Sep 17 00:00:00 2001 From: Cyrus Nikolaidis Date: Wed, 6 Dec 2023 17:57:55 -0800 Subject: [PATCH] Quick tweak on readme Summary: Some messiness in rebase made through the previous diff. Reviewed By: csahana95 Differential Revision: D51924306 fbshipit-source-id: 320583e1c62b00421f2d46c627e1514399acd821 --- CybersecurityBenchmarks/README.md | 9 --------- 1 file changed, 9 deletions(-) diff --git a/CybersecurityBenchmarks/README.md b/CybersecurityBenchmarks/README.md index 8aeba5dd5..7b1f77d82 100644 --- a/CybersecurityBenchmarks/README.md +++ b/CybersecurityBenchmarks/README.md @@ -117,15 +117,6 @@ python3 -m CybersecurityBenchmarks.benchmark.run \ --llm-under-test= --llm-under-test= ... [--run-llm-in-parallel] ``` -<<<<<<< dest: b69196565c8c - bbhushanam: [Easy][Pre Ranked Ads] Set Max Con... -Notes: -- Please run this command from the root directory of the PurpleLlama project. -||||||| base: 5c24c36f00ca - danielsong: [PurpleLllama] More MITRE benchmar... - -(`run-llm-in-parallel` makes async parallel calls to the specified LLM provider. This speeds up prompt evaluation) -======= - ->>>>>>> source: ad1c12633cbf - cyni: readme number 2 Both the instruct and autocomplete benchmarks are run in two steps: