2025-09-30 14:53:21 +00:00
|
|
|
# qa
|
2025-10-01 13:11:54 +00:00
|
|
|
WANDB_MODE=disabled uv run run_eval.py --model_name_or_path google/gemma-2-2b-it --datasets squad drop ropes --split test --use_cd --cd_update_iterations 300 --eval_batch_size_gen=1 --truncate_if_too_long_inp
|
2025-09-30 14:53:21 +00:00
|
|
|
|
|
|
|
|
|
|
|
|
|
# longbench
|
2026-06-15 04:31:47 +00:00
|
|
|
WANDB_MODE=disabled uv run run_eval.py --model_name_or_path google/gemma-2-2b-it --datasets longbench/multifieldqa_en_e longbench/2wikimqa_e longbench/qasper_e longbench/gov_report_e --split test --use_cd --cd_update_iterations 300 --eval_batch_size_gen=1 --truncate_if_too_long_inp
|
