isakzhang's picture
update scripts
60867e4
|
raw
history blame
569 Bytes
metadata
license: apache-2.0
language:
  - en
  - zh
  - vi
  - id
  - th
size_categories:
  - n<1K
configs:
  - config_name: results
    data_files: SeaExam_results.csv

About

This repo contains the original results for the space SeaExam Leaderboard.

To reproduce our results, use the script in this repo. The script will download the model and tokenizer, and evaluate the model on the benchmark data.

python scripts/main.py --model $model_name_or_path