From d2ba68d48ea3119663755c933c2e1f3ef30a6527 Mon Sep 17 00:00:00 2001 From: ncoop57 Date: Sat, 9 Oct 2021 17:12:06 +0000 Subject: [PATCH] Add example for evaluation --- evaluation/README.md | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/evaluation/README.md b/evaluation/README.md index e524be0..af9017b 100644 --- a/evaluation/README.md +++ b/evaluation/README.md @@ -18,4 +18,8 @@ With the following requirements performed you can now run the `evaluation.py` sc ``` python evaluate.py --model_name_or_path=model_name_or_path --human_eval_path= --out_path=./model_results ``` -So for example if you want to evaluate the EleutherAI GPT Neo 125M \ No newline at end of file + +So for example if you want to evaluate the EleutherAI GPT Neo 125M +``` +python evaluate.py EleutherAI/gpt-neo-125M ../dependency_repos/human-eval/data/HumanEval.jsonl.gz model_results/ +``` \ No newline at end of file