diff options
Diffstat (limited to 'README.md')
| -rw-r--r-- | README.md | 9 |
1 files changed, 0 insertions, 9 deletions
@@ -2,15 +2,12 @@ <a href='https://arxiv.org/abs/2505.20282'><img src='https://img.shields.io/badge/arXiv-2505.20282-b31b1b.svg'></a> ---- - ### Reproducing One-shot EM Training (SOTA) ```bash accelerate launch train.py --lr 2e-5 --temperature 0.5 --bsz 64 ``` ---- ### Reproducing Multi-shot EM Training @@ -18,8 +15,6 @@ accelerate launch train.py --lr 2e-5 --temperature 0.5 --bsz 64 accelerate launch train.py --lr 2e-5 --temperature 0.5 --bsz 64 --data_path "dataset/numina/numina_00.parquet" ``` ---- - ### Evaluation ```bash @@ -27,8 +22,6 @@ cd Qwen2.5-Eval/evaluation bash sh/eval_all_math.sh ``` ---- - ### Acknowledgements Our dataset references and builds upon the following open-source contributions: @@ -41,8 +34,6 @@ Our dataset references and builds upon the following open-source contributions: We sincerely thank the authors and maintainers of these projects for their excellent contributions to the research community! ---- - ### Citation ``` @misc{gao2025oneshotentropyminimization, |