Views
No views yet
Cloned from https://github.com/amazon-science/mm-cot

pip install -r requirements.txthttps://github.com/lupantech/ScienceQA/tree/main/datavision_features# rationale generation
CUDA_VISIBLE_DEVICES=0,1 python main.py \
--model allenai/unifiedqa-t5-base \
--user_msg rationale --img_type detr \
--bs 8 --eval_bs 4 --eval_acc 10 --output_len 512 \
--final_eval --prompt_format QCM-LE
# answer inference
CUDA_VISIBLE_DEVICES=0,1 python main.py \
--model allenai/unifiedqa-t5-base \
--user_msg answer --img_type detr \
--bs 8 --eval_bs 4 --eval_acc 10 --output_len 64 \
--final_eval --prompt_format QCMG-A \
--eval_le experiments/rationale_allenai-unifiedqa-t5-base_detr_QCM-LE_lr5e-05_bs16_op512_ep20/predictions_ans_eval.json \
--test_le experiments/rationale_allenai-unifiedqa-t5-base_detr_QCM-LE_lr5e-05_bs16_op512_ep20/predictions_ans_test.jsonmodels folder.# rationale generation
CUDA_VISIBLE_DEVICES=0,1 python main.py \
--model allenai/unifiedqa-t5-base \
--user_msg rationale --img_type detr \
--bs 8 --eval_bs 4 --eval_acc 10 --output_len 512 \
--final_eval --prompt_format QCM-LE \
--evaluate_dir models/MM-CoT-UnifiedQA-base-Rationale
# answer inference
CUDA_VISIBLE_DEVICES=0,1 python main.py \
--model allenai/unifiedqa-t5-base \
--user_msg answer --img_type detr \
--bs 8 --eval_bs 4 --eval_acc 10 --output_len 64 \
--final_eval --prompt_format QCMG-A \
--eval_le models/rationale/predictions_ans_eval.json \
--test_le models/rationale/predictions_ans_test.json \
--evaluate_dir models/MM-CoT-UnifiedQA-base-Answer@article{zhang2023multicot,
title={Multimodal Chain-of-Thought Reasoning in Language Models},
author={Zhang, Zhuosheng and Zhang, Aston and Li, Mu and Zhao, Hai and Karypis, George and Smola, Alex},
journal={arXiv preprint arXiv:2302.00923},
year={2023}
}