transformers torch-optimizer datasets scikit-learn>=1.5.0 scipy>=1.12.0 numpy==1.26.4 pandas==1.4.0 tqdm>=4.66.4 rdkit>=2024.3.5 triton==2.2.0 causal-conv1d==1.1.3.post1 mamba_ssm==1.1.3.post1