multimer
Datasets
All datasets matching “multimer”kfold-multimer-lmdb
kfold-multimer-lmdb
Training data for the multimer / protein-ligand fine-tune in
hsjang0/k-fold-multimer-tuning.
Pre-tokenized complexes as LMDB, plus the eval splits and label tables the configs read.
Do not clone the whole thing to run one experiment. It is 201 GB and a single arm reads a
handful of its sources. The repo's scripts/fetch_data.py takes a config name, works out
which sources that config actually needs, and pulls only those.
python scripts/fetch_data.py --config… See the full description on the dataset page: https://huggingface.co/datasets/hyosoon0/kfold-multimer-lmdb.details_allknowingroger__Multimerge-12B-MoE
Dataset Card for Evaluation run of allknowingroger/Multimerge-12B-MoE
Dataset automatically created during the evaluation run of model allknowingroger/Multimerge-12B-MoE on the Open LLM Leaderboard.
The dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_allknowingroger__Multimerge-12B-MoE.details_allknowingroger__Multimerge-Neurallaymons-12B-MoE
Dataset Card for Evaluation run of allknowingroger/Multimerge-Neurallaymons-12B-MoE
Dataset automatically created during the evaluation run of model allknowingroger/Multimerge-Neurallaymons-12B-MoE on the Open LLM Leaderboard.
The dataset is composed of 63 configuration, each one coresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_allknowingroger__Multimerge-Neurallaymons-12B-MoE.train_A100_multimer_816
Corrected full dataset and fixed 10% subset
This repository replaces the previous flawed multimer-only export with the corrected
train_A100_816 dataset and its fixed, uniformly sampled _10p subset. The repository
name is retained for continuity; the replacement includes both monomers and multimers.
Downloads
Archive
Contents
train_A100_816.tar.gz
Complete corrected export: 154,172 unique structure pickles, all full and _10p metadata, preprocessing… See the full description on the dataset page: https://huggingface.co/datasets/raftbioworks/train_A100_multimer_816.allknowingroger__MultiMerge-7B-slerp-details
Dataset Card for Evaluation run of allknowingroger/MultiMerge-7B-slerp
Dataset automatically created during the evaluation run of model allknowingroger/MultiMerge-7B-slerp
The dataset is composed of 38 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/allknowingroger__MultiMerge-7B-slerp-details.allknowingroger__Multimerge-19B-pass-details
Dataset Card for Evaluation run of allknowingroger/Multimerge-19B-pass
Dataset automatically created during the evaluation run of model allknowingroger/Multimerge-19B-pass
The dataset is composed of 38 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 1 run(s). Each run can be found as a specific split in each configuration, the split being named using the timestamp of the run.The "train" split is always pointing to the latest… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/allknowingroger__Multimerge-19B-pass-details.