From 289cc99cd6717155573f8a40cba8cf6a56315ea2 Mon Sep 17 00:00:00 2001 From: Wenjing Margaret Mao Date: Tue, 9 Apr 2024 16:01:12 +0800 Subject: [PATCH] Update README.md (#10700) Edit "summarize the results" --- python/llm/dev/benchmark/harness/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/python/llm/dev/benchmark/harness/README.md b/python/llm/dev/benchmark/harness/README.md index 4dfcf09a..50ec4b86 100644 --- a/python/llm/dev/benchmark/harness/README.md +++ b/python/llm/dev/benchmark/harness/README.md @@ -30,6 +30,6 @@ Taking example above, the script will fork 3 processes, each for one xpu, to exe ## Results We follow [Open LLM Leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard) to record our metrics, `acc_norm` for `hellaswag` and `arc_challenge`, `mc2` for `truthful_qa` and `acc` for `mmlu`. For `mmlu`, there are 57 subtasks which means users may need to average them manually to get final result. ## Summarize the results -"""python +```python python make_table.py -""" \ No newline at end of file +```