datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
OpenAssistant__oasst-sft-1-pythia-12b-details
Dataset Card for Evaluation run of OpenAssistant/oasst-sft-1-pythia-12b
Dataset automatically created during the evaluation run of model OpenAssistant/oasst-sft-1-pythia-12b
The dataset is composed of 44 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/OpenAssistant__oasst-sft-1-pythia-12b-details.EleutherAI__pythia-1.4b-details
Dataset Card for Evaluation run of EleutherAI/pythia-1.4b
Dataset automatically created during the evaluation run of model EleutherAI/pythia-1.4b
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 results.
An additional… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/EleutherAI__pythia-1.4b-details.EleutherAI__pythia-160m-details
Dataset Card for Evaluation run of EleutherAI/pythia-160m
Dataset automatically created during the evaluation run of model EleutherAI/pythia-160m
The dataset is composed of 44 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 2 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 results.
An additional… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/EleutherAI__pythia-160m-details.pythia-paths-evidence
Pythia Paths Evidence
A small, revision-pinned evidence bundle for examining model-training paths
without converting a trend into authority.
Companion read-only interface: Pythia Paths Static Space
(mutable navigation; the evidence files below remain digest-pinned).
Initial scope
Model: EleutherAI/pythia-70m-deduped
Run: the default public run only
Context coverage: all 27 zero-shot reports in one pinned directory
Detailed coverage: four post-outcome-selected… See the full description on the dataset page: https://huggingface.co/datasets/Yu-and-Ai/pythia-paths-evidence.EleutherAI__pythia-12b-details
Dataset Card for Evaluation run of EleutherAI/pythia-12b
Dataset automatically created during the evaluation run of model EleutherAI/pythia-12b
The dataset is composed of 44 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 results.
An additional… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/EleutherAI__pythia-12b-details.EleutherAI__pythia-410m-details
Dataset Card for Evaluation run of EleutherAI/pythia-410m
Dataset automatically created during the evaluation run of model EleutherAI/pythia-410m
The dataset is composed of 44 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 2 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 results.
An additional… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/EleutherAI__pythia-410m-details.EleutherAI__pythia-6.9b-details
Dataset Card for Evaluation run of EleutherAI/pythia-6.9b
Dataset automatically created during the evaluation run of model EleutherAI/pythia-6.9b
The dataset is composed of 44 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 2 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 results.
An additional… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/EleutherAI__pythia-6.9b-details.EleutherAI__pythia-2.8b-details
Dataset Card for Evaluation run of EleutherAI/pythia-2.8b
Dataset automatically created during the evaluation run of model EleutherAI/pythia-2.8b
The dataset is composed of 44 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 results.
An additional… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/EleutherAI__pythia-2.8b-details.EleutherAI__pythia-1b-details
Dataset Card for Evaluation run of EleutherAI/pythia-1b
Dataset automatically created during the evaluation run of model EleutherAI/pythia-1b
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 results.
An additional… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/EleutherAI__pythia-1b-details.jaredjoss__pythia-410m-roberta-lr_8e7-kl_01-steps_12000-rlhf-model-details
Dataset Card for Evaluation run of jaredjoss/pythia-410m-roberta-lr_8e7-kl_01-steps_12000-rlhf-model
Dataset automatically created during the evaluation run of model jaredjoss/pythia-410m-roberta-lr_8e7-kl_01-steps_12000-rlhf-model
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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/jaredjoss__pythia-410m-roberta-lr_8e7-kl_01-steps_12000-rlhf-model-details.