datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
details_KoboldAI__OPT-6B-nerys-v2
Dataset Card for Evaluation run of KoboldAI/OPT-6B-nerys-v2
Dataset Summary
Dataset automatically created during the evaluation run of model KoboldAI/OPT-6B-nerys-v2 on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_KoboldAI__OPT-6B-nerys-v2.details_KoboldAI__LLaMA2-13B-Estopia
Dataset Card for Evaluation run of KoboldAI/LLaMA2-13B-Estopia
Dataset automatically created during the evaluation run of model KoboldAI/LLaMA2-13B-Estopia 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 3 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_KoboldAI__LLaMA2-13B-Estopia.details_KoboldAI__fairseq-dense-2.7B
Dataset Card for Evaluation run of KoboldAI/fairseq-dense-2.7B
Dataset Summary
Dataset automatically created during the evaluation run of model KoboldAI/fairseq-dense-2.7B on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding 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"… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_KoboldAI__fairseq-dense-2.7B.details_KoboldAI__fairseq-dense-6.7B
Dataset Card for Evaluation run of KoboldAI/fairseq-dense-6.7B
Dataset Summary
Dataset automatically created during the evaluation run of model KoboldAI/fairseq-dense-6.7B on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding 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"… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_KoboldAI__fairseq-dense-6.7B.details_KoboldAI__fairseq-dense-355M
Dataset Card for Evaluation run of KoboldAI/fairseq-dense-355M
Dataset Summary
Dataset automatically created during the evaluation run of model KoboldAI/fairseq-dense-355M on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding 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"… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_KoboldAI__fairseq-dense-355M.details_KoboldAI__Mistral-7B-Holodeck-1
Dataset Card for Evaluation run of KoboldAI/Mistral-7B-Holodeck-1
Dataset automatically created during the evaluation run of model KoboldAI/Mistral-7B-Holodeck-1 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_KoboldAI__Mistral-7B-Holodeck-1.details_KoboldAI__fairseq-dense-125M
Dataset Card for Evaluation run of KoboldAI/fairseq-dense-125M
Dataset Summary
Dataset automatically created during the evaluation run of model KoboldAI/fairseq-dense-125M on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding 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"… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_KoboldAI__fairseq-dense-125M.details_KoboldAI__OPT-2.7B-Nerys-v2
Dataset Card for Evaluation run of KoboldAI/OPT-2.7B-Nerys-v2
Dataset Summary
Dataset automatically created during the evaluation run of model KoboldAI/OPT-2.7B-Nerys-v2 on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_KoboldAI__OPT-2.7B-Nerys-v2.details_KoboldAI__LLaMA2-13B-Tiefighter
Dataset Card for Evaluation run of KoboldAI/LLaMA2-13B-Tiefighter
Dataset Summary
Dataset automatically created during the evaluation run of model KoboldAI/LLaMA2-13B-Tiefighter on the Open LLM Leaderboard.
The dataset is composed of 64 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_KoboldAI__LLaMA2-13B-Tiefighter.details_KoboldAI__Mixtral-8x7B-Holodeck-v1
Dataset Card for Evaluation run of KoboldAI/Mixtral-8x7B-Holodeck-v1
Dataset automatically created during the evaluation run of model KoboldAI/Mixtral-8x7B-Holodeck-v1 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_KoboldAI__Mixtral-8x7B-Holodeck-v1.details_KoboldAI__PPO_Pygway-6b-Mix
Dataset Card for Evaluation run of KoboldAI/PPO_Pygway-6b-Mix
Dataset Summary
Dataset automatically created during the evaluation run of model KoboldAI/PPO_Pygway-6b-Mix on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_KoboldAI__PPO_Pygway-6b-Mix.details_KoboldAI__GPT-NeoX-20B-Erebus
Dataset Card for Evaluation run of KoboldAI/GPT-NeoX-20B-Erebus
Dataset Summary
Dataset automatically created during the evaluation run of model KoboldAI/GPT-NeoX-20B-Erebus on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding 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"… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_KoboldAI__GPT-NeoX-20B-Erebus.details_KoboldAI__OPT-2.7B-Nerybus-Mix
Dataset Card for Evaluation run of KoboldAI/OPT-2.7B-Nerybus-Mix
Dataset Summary
Dataset automatically created during the evaluation run of model KoboldAI/OPT-2.7B-Nerybus-Mix on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding 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"… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_KoboldAI__OPT-2.7B-Nerybus-Mix.details_KoboldAI__GPT-J-6B-Janeway
Dataset Card for Evaluation run of KoboldAI/GPT-J-6B-Janeway
Dataset Summary
Dataset automatically created during the evaluation run of model KoboldAI/GPT-J-6B-Janeway on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_KoboldAI__GPT-J-6B-Janeway.details_KoboldAI__OPT-6.7B-Erebus
Dataset Card for Evaluation run of KoboldAI/OPT-6.7B-Erebus
Dataset Summary
Dataset automatically created during the evaluation run of model KoboldAI/OPT-6.7B-Erebus on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_KoboldAI__OPT-6.7B-Erebus.details_KoboldAI__OPT-350M-Erebus
Dataset Card for Evaluation run of KoboldAI/OPT-350M-Erebus
Dataset Summary
Dataset automatically created during the evaluation run of model KoboldAI/OPT-350M-Erebus on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_KoboldAI__OPT-350M-Erebus.details_KoboldAI__OPT-13B-Nerybus-Mix
Dataset Card for Evaluation run of KoboldAI/OPT-13B-Nerybus-Mix
Dataset Summary
Dataset automatically created during the evaluation run of model KoboldAI/OPT-13B-Nerybus-Mix on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding 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"… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_KoboldAI__OPT-13B-Nerybus-Mix.details_KoboldAI__GPT-NeoX-20B-Skein
Dataset Card for Evaluation run of KoboldAI/GPT-NeoX-20B-Skein
Dataset Summary
Dataset automatically created during the evaluation run of model KoboldAI/GPT-NeoX-20B-Skein on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding 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"… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_KoboldAI__GPT-NeoX-20B-Skein.details_KoboldAI__GPT-J-6B-Adventure
Dataset Card for Evaluation run of KoboldAI/GPT-J-6B-Adventure
Dataset Summary
Dataset automatically created during the evaluation run of model KoboldAI/GPT-J-6B-Adventure on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding 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"… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_KoboldAI__GPT-J-6B-Adventure.details_KoboldAI__GPT-J-6B-Skein
Dataset Card for Evaluation run of KoboldAI/GPT-J-6B-Skein
Dataset Summary
Dataset automatically created during the evaluation run of model KoboldAI/GPT-J-6B-Skein on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_KoboldAI__GPT-J-6B-Skein.details_KoboldAI__OPT-13B-Nerys-v2
Dataset Card for Evaluation run of KoboldAI/OPT-13B-Nerys-v2
Dataset Summary
Dataset automatically created during the evaluation run of model KoboldAI/OPT-13B-Nerys-v2 on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_KoboldAI__OPT-13B-Nerys-v2.details_KoboldAI__OPT-30B-Erebus
Dataset Card for Evaluation run of KoboldAI/OPT-30B-Erebus
Dataset Summary
Dataset automatically created during the evaluation run of model KoboldAI/OPT-30B-Erebus on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_KoboldAI__OPT-30B-Erebus.details_KoboldAI__LLaMA2-13B-Psyfighter2
Dataset Card for Evaluation run of KoboldAI/LLaMA2-13B-Psyfighter2
Dataset Summary
Dataset automatically created during the evaluation run of model KoboldAI/LLaMA2-13B-Psyfighter2 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_KoboldAI__LLaMA2-13B-Psyfighter2.details_KoboldAI__OPT-6.7B-Nerybus-Mix
Dataset Card for Evaluation run of KoboldAI/OPT-6.7B-Nerybus-Mix
Dataset Summary
Dataset automatically created during the evaluation run of model KoboldAI/OPT-6.7B-Nerybus-Mix on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding 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"… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_KoboldAI__OPT-6.7B-Nerybus-Mix.details_KoboldAI__GPT-J-6B-Shinen
Dataset Card for Evaluation run of KoboldAI/GPT-J-6B-Shinen
Dataset Summary
Dataset automatically created during the evaluation run of model KoboldAI/GPT-J-6B-Shinen on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_KoboldAI__GPT-J-6B-Shinen.details_KoboldAI__OPT-2.7B-Erebus
Dataset Card for Evaluation run of KoboldAI/OPT-2.7B-Erebus
Dataset Summary
Dataset automatically created during the evaluation run of model KoboldAI/OPT-2.7B-Erebus on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_KoboldAI__OPT-2.7B-Erebus.details_KoboldAI__OPT-13B-Erebus
Dataset Card for Evaluation run of KoboldAI/OPT-13B-Erebus
Dataset Summary
Dataset automatically created during the evaluation run of model KoboldAI/OPT-13B-Erebus on the Open LLM Leaderboard.
The dataset is composed of 64 configuration, each one coresponding 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_KoboldAI__OPT-13B-Erebus.details_KoboldAI__fairseq-dense-1.3B
Dataset Card for Evaluation run of KoboldAI/fairseq-dense-1.3B
Dataset Summary
Dataset automatically created during the evaluation run of model KoboldAI/fairseq-dense-1.3B on the Open LLM Leaderboard.
The dataset is composed of 3 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_KoboldAI__fairseq-dense-1.3B.infinity3m-koboExperimental upload of a modified version of the BAAI/Infinity-Instruct 3M dataset.
Filtering tools were used to cut down on foreign languages, refusals and writing tasks.
While the removal of writing tasks is unusual for our community this allows tuners to use this dataset alongside superior writing data, preventing short story biases from being inserted.
details_KoboldAI__fairseq-dense-13B
Dataset Card for Evaluation run of KoboldAI/fairseq-dense-13B
Dataset Summary
Dataset automatically created during the evaluation run of model KoboldAI/fairseq-dense-13B on the Open LLM Leaderboard.
The dataset is composed of 3 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_KoboldAI__fairseq-dense-13B.