From fb4f530bf5004a9afef1380cb0a84bfb98a89c63 Mon Sep 17 00:00:00 2001 From: Cade Daniel Date: Tue, 30 Jul 2024 16:28:49 -0700 Subject: [PATCH] [CI] [nightly benchmark] Do not re-download sharegpt dataset if exists (#6706) --- .buildkite/nightly-benchmarks/run-benchmarks-suite.sh | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/.buildkite/nightly-benchmarks/run-benchmarks-suite.sh b/.buildkite/nightly-benchmarks/run-benchmarks-suite.sh index 53a45b90b15f..1a88d038b4b5 100644 --- a/.buildkite/nightly-benchmarks/run-benchmarks-suite.sh +++ b/.buildkite/nightly-benchmarks/run-benchmarks-suite.sh @@ -34,6 +34,15 @@ check_hf_token() { fi } +ensure_sharegpt_downloaded() { + local FILE=ShareGPT_V3_unfiltered_cleaned_split.json + if [ ! -f "$FILE" ]; then + wget https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/$FILE + else + echo "$FILE already exists." + fi +} + json2args() { # transforms the JSON string to command line args, and '_' is replaced to '-' # example: @@ -350,7 +359,7 @@ main() { # prepare for benchmarking cd benchmarks || exit 1 - wget https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json + ensure_sharegpt_downloaded declare -g RESULTS_FOLDER=results/ mkdir -p $RESULTS_FOLDER QUICK_BENCHMARK_ROOT=../.buildkite/nightly-benchmarks/