From db1810b8fb615bdd5ca44de1848e37ba8746ec09 Mon Sep 17 00:00:00 2001 From: yan-gao-GY Date: Fri, 6 Sep 2024 22:19:10 +0100 Subject: [PATCH] Update readme --- benchmarks/flowertune-llm/evaluation/code/README.md | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/benchmarks/flowertune-llm/evaluation/code/README.md b/benchmarks/flowertune-llm/evaluation/code/README.md index 28c0634cb17d..2d1373d79884 100644 --- a/benchmarks/flowertune-llm/evaluation/code/README.md +++ b/benchmarks/flowertune-llm/evaluation/code/README.md @@ -18,9 +18,6 @@ pip install -r requirements.txt # Log in HuggingFace account huggingface-cli login - -# Download main.py script -git clone https://github.com/bigcode-project/bigcode-evaluation-harness.git && cd bigcode-evaluation-harness && git checkout 0f3e95f0806e78a4f432056cdb1be93604a51d69 && mv main.py ../ && cd .. && rm -rf bigcode-evaluation-harness ``` After that, install `Node.js` and `g++` for the evaluation of JavaScript, C++: @@ -36,6 +33,12 @@ nvm install 20 sudo apt-get install g++ ``` +Then, download the `main.py` script from `bigcode-evaluation-harness` repository. + +```shell +git clone https://github.com/bigcode-project/bigcode-evaluation-harness.git && cd bigcode-evaluation-harness && git checkout 0f3e95f0806e78a4f432056cdb1be93604a51d69 && mv main.py ../ && cd .. && rm -rf bigcode-evaluation-harness +``` + ## Generate model answers & calculate pass@1 score