datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
met-office-uk-deterministic-solar
Met Office UK Deterministic Dataset (Zarr Format)
Description
This dataset is a subset of the Met Office UK Deterministic Dataset, converted from the original NetCDF format into Zarr format for modern data analysis. The Zarr files are packaged as .zarr.zip archives for efficient storage and transfer.
The subset focuses on specific variables and configurations, which are detailed below. Researchers and developers can use this subset for applications in climate science… See the full description on the dataset page: https://huggingface.co/datasets/openclimatefix/met-office-uk-deterministic-solar.details_fblgit__UNA-SOLAR-10.7B-Instruct-v1.0
Dataset Card for Evaluation run of fblgit/UNA-SOLAR-10.7B-Instruct-v1.0
Dataset automatically created during the evaluation run of model fblgit/UNA-SOLAR-10.7B-Instruct-v1.0 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 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_fblgit__UNA-SOLAR-10.7B-Instruct-v1.0.details_LDCC__LDCC-SOLAR-10.7B
Dataset Card for Evaluation run of LDCC/LDCC-SOLAR-10.7B
Dataset automatically created during the evaluation run of model LDCC/LDCC-SOLAR-10.7B 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 the latest… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_LDCC__LDCC-SOLAR-10.7B.details_dddsaty__SOLAR-Instruct-ko-Adapter-Attach
Dataset Card for Evaluation run of dddsaty/SOLAR-Instruct-ko-Adapter-Attach
Dataset automatically created during the evaluation run of model dddsaty/SOLAR-Instruct-ko-Adapter-Attach 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 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_dddsaty__SOLAR-Instruct-ko-Adapter-Attach.details_upstage__SOLAR-10.7B-v1.0
Dataset Card for Evaluation run of upstage/SOLAR-10.7B-v1.0
Dataset automatically created during the evaluation run of model upstage/SOLAR-10.7B-v1.0 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 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_upstage__SOLAR-10.7B-v1.0.3_4_fusechat_v1_openchat-3.5_nh2-mixtral-8x7b-dpo_nh2-solar-10.7b_representation1_4_fusechat_v1_openchat-3.5_nh2-mixtral-8x7b-dpo_nh2-solar-10.7b_representationdetails_jilp00__Hermes-2-SOLAR-10.7B-Symbolic
Dataset Card for Evaluation run of jilp00/Hermes-2-SOLAR-10.7B-Symbolic
Dataset automatically created during the evaluation run of model jilp00/Hermes-2-SOLAR-10.7B-Symbolic 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_jilp00__Hermes-2-SOLAR-10.7B-Symbolic.3_4_fusechat_v1_openchat-3.5_mixtral-8x7b-instruct-v0.1_solar-10.7b-instruct-v1.0_representationdetails_krevas__SOLAR-10.7B
Dataset Card for Evaluation run of krevas/SOLAR-10.7B
Dataset automatically created during the evaluation run of model krevas/SOLAR-10.7B 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 pointing to the latest results.… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_krevas__SOLAR-10.7B.details_bn22__Nous-Hermes-2-SOLAR-10.7B-MISALIGNED
Dataset Card for Evaluation run of bn22/Nous-Hermes-2-SOLAR-10.7B-MISALIGNED
Dataset automatically created during the evaluation run of model bn22/Nous-Hermes-2-SOLAR-10.7B-MISALIGNED 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"… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_bn22__Nous-Hermes-2-SOLAR-10.7B-MISALIGNED.details_Sao10K__Sensualize-Solar-10.7B
Dataset Card for Evaluation run of Sao10K/Sensualize-Solar-10.7B
Dataset automatically created during the evaluation run of model Sao10K/Sensualize-Solar-10.7B 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 pointing… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_Sao10K__Sensualize-Solar-10.7B.details_vicgalle__franken-SOLAR-18B-v1.0
Dataset Card for Evaluation run of vicgalle/franken-SOLAR-18B-v1.0
Dataset automatically created during the evaluation run of model vicgalle/franken-SOLAR-18B-v1.0 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_vicgalle__franken-SOLAR-18B-v1.0.details_pinkyponky__SOLAR-10.7B-dpo-instruct-tuned-v0.1
Dataset Card for Evaluation run of pinkyponky/SOLAR-10.7B-dpo-instruct-tuned-v0.1
Dataset automatically created during the evaluation run of model pinkyponky/SOLAR-10.7B-dpo-instruct-tuned-v0.1 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_pinkyponky__SOLAR-10.7B-dpo-instruct-tuned-v0.1.OpenOrca_Solar_filtered
TODO
To be consistent, we need to change column name into ['instruction', 'input', 'output'], which is same as alpaca-gpt4.
Dataset Summary
This is a filtered version of OpenOrca dataset based on Solar 10.7B paper.
In this version, of the 4.2M OpenOrca data, 113k data is removed.
In more conservative version here, of the 4.2M OpenOrca data, 117k data is removed.
Step 1
FLAN data link broken
Based on DataProvenanceInitiative/flan2021_submix_original… See the full description on the dataset page: https://huggingface.co/datasets/ChuGyouk/OpenOrca_Solar_filtered.details_Sao10K__SOLAR-10.7B-NahIdWin
Dataset Card for Evaluation run of Sao10K/SOLAR-10.7B-NahIdWin
Dataset automatically created during the evaluation run of model Sao10K/SOLAR-10.7B-NahIdWin 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 pointing to… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_Sao10K__SOLAR-10.7B-NahIdWin.details_dillfrescott__Nous-Hermes-2-SOLAR-10.7B-x2-MoE
Dataset Card for Evaluation run of dillfrescott/Nous-Hermes-2-SOLAR-10.7B-x2-MoE
Dataset automatically created during the evaluation run of model dillfrescott/Nous-Hermes-2-SOLAR-10.7B-x2-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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_dillfrescott__Nous-Hermes-2-SOLAR-10.7B-x2-MoE.details_NousResearch__Nous-Hermes-2-SOLAR-10.7B
Dataset Card for Evaluation run of NousResearch/Nous-Hermes-2-SOLAR-10.7B
Dataset automatically created during the evaluation run of model NousResearch/Nous-Hermes-2-SOLAR-10.7B 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_NousResearch__Nous-Hermes-2-SOLAR-10.7B.details_Walmart-the-bag__Solar-10.7B-Cato
Dataset Card for Evaluation run of Walmart-the-bag/Solar-10.7B-Cato
Dataset automatically created during the evaluation run of model Walmart-the-bag/Solar-10.7B-Cato 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_Walmart-the-bag__Solar-10.7B-Cato.details_upstage__SOLAR-0-70b-16bit
Dataset Card for Evaluation run of upstage/SOLAR-0-70b-16bit
Dataset Summary
Dataset automatically created during the evaluation run of model upstage/SOLAR-0-70b-16bit 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 is… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_upstage__SOLAR-0-70b-16bit.details_macadeliccc__Orca-SOLAR-4x10.7b
Dataset Card for Evaluation run of macadeliccc/Orca-SOLAR-4x10.7b
Dataset automatically created during the evaluation run of model macadeliccc/Orca-SOLAR-4x10.7b 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_macadeliccc__Orca-SOLAR-4x10.7b.details_maywell__PiVoT-SOLAR-10.7B-RP
Dataset Card for Evaluation run of maywell/PiVoT-SOLAR-10.7B-RP
Dataset automatically created during the evaluation run of model maywell/PiVoT-SOLAR-10.7B-RP 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 pointing to… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_maywell__PiVoT-SOLAR-10.7B-RP.details_sumo43__SOLAR-10.7B-Instruct-DPO-v1.0
Dataset Card for Evaluation run of sumo43/SOLAR-10.7B-Instruct-DPO-v1.0
Dataset automatically created during the evaluation run of model sumo43/SOLAR-10.7B-Instruct-DPO-v1.0 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_sumo43__SOLAR-10.7B-Instruct-DPO-v1.0.details_kimwooglae__AISquare-Instruct-SOLAR-10.7b-v0.5.32
Dataset Card for Evaluation run of kimwooglae/AISquare-Instruct-SOLAR-10.7b-v0.5.32
Dataset automatically created during the evaluation run of model kimwooglae/AISquare-Instruct-SOLAR-10.7b-v0.5.32 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_kimwooglae__AISquare-Instruct-SOLAR-10.7b-v0.5.32.details_kihoonlee__stock-solar-10.7b-v1details_jan-ai__Solar-10.7B-SLERP
Dataset Card for Evaluation run of jan-ai/Solar-10.7B-SLERP
Dataset automatically created during the evaluation run of model jan-ai/Solar-10.7B-SLERP 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 pointing to the… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_jan-ai__Solar-10.7B-SLERP.details_Weyaxi__HelpSteer-filtered-Solar-Instruct
Dataset Card for Evaluation run of Weyaxi/HelpSteer-filtered-Solar-Instruct
Dataset automatically created during the evaluation run of model Weyaxi/HelpSteer-filtered-Solar-Instruct 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"… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_Weyaxi__HelpSteer-filtered-Solar-Instruct.0_4_fusechat_v1_openchat-3.5_nh2-mixtral-8x7b-dpo_nh2-solar-10.7b_representationdetails_bhavinjawade__SOLAR-10B-OrcaDPO-Jawade
Dataset Card for Evaluation run of bhavinjawade/SOLAR-10B-OrcaDPO-Jawade
Dataset automatically created during the evaluation run of model bhavinjawade/SOLAR-10B-OrcaDPO-Jawade 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 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_bhavinjawade__SOLAR-10B-OrcaDPO-Jawade.details_Changgil__K2S3-SOLAR-11b-v4.0
Dataset Card for Evaluation run of Changgil/K2S3-SOLAR-11b-v4.0
Dataset automatically created during the evaluation run of model Changgil/K2S3-SOLAR-11b-v4.0 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 pointing to… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_Changgil__K2S3-SOLAR-11b-v4.0.