Files
alibaba-nlp--deepresearch/WebAgent/WebWatcher/infer/evaluation/run_eval.sh
T
2026-07-13 13:26:09 +08:00

7 lines
171 B
Bash

export API_KEY=$1
export BASE_URL=$2
export JUDGE_MODEL=$3
export MAX_WORKERS=$4
python evaluation/evaluate_hle_official.py \
--input_fp YOUR_PREDICTIONS_FILE.jsonl \