Views
No views yet
run_minimal_pipeline.sh)scripts/validate_u2_schema.py)scripts/evaluate_predictions.py)requirements.txt)1python -m venv .venv
2source .venv/bin/activate
3pip install -r requirements.txt
4python scripts/validate_u2_schema.py --input data/u2_bench_non_stem_qa.jsonl1python scripts/evaluate_predictions.py \
2 --gold data/u2_bench_non_stem_qa.jsonl \
3 --predictions data/predictions.jsonl./run_minimal_pipeline.sh data/u2_bench_non_stem_qa.jsonl data/predictions.jsonlqhashquestiongold_answerevaluate_predictions.py must contain:qhashpredicted