datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
jpacifico__Chocolatine-14B-Instruct-4k-DPO-details
Dataset Card for Evaluation run of jpacifico/Chocolatine-14B-Instruct-4k-DPO
Dataset automatically created during the evaluation run of model jpacifico/Chocolatine-14B-Instruct-4k-DPO
The dataset is composed of 38 configuration(s), each one corresponding to one of the evaluated task.
The dataset has been created from 5 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/jpacifico__Chocolatine-14B-Instruct-4k-DPO-details.jpacifico__Chocolatine-3B-Instruct-DPO-v1.0-details
Dataset Card for Evaluation run of jpacifico/Chocolatine-3B-Instruct-DPO-v1.0
Dataset automatically created during the evaluation run of model jpacifico/Chocolatine-3B-Instruct-DPO-v1.0
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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/jpacifico__Chocolatine-3B-Instruct-DPO-v1.0-details.jpacifico__Chocolatine-3B-Instruct-DPO-v1.2-details
Dataset Card for Evaluation run of jpacifico/Chocolatine-3B-Instruct-DPO-v1.2
Dataset automatically created during the evaluation run of model jpacifico/Chocolatine-3B-Instruct-DPO-v1.2
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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/jpacifico__Chocolatine-3B-Instruct-DPO-v1.2-details.jpacifico__Chocolatine-14B-Instruct-DPO-v1.2-details
Dataset Card for Evaluation run of jpacifico/Chocolatine-14B-Instruct-DPO-v1.2
Dataset automatically created during the evaluation run of model jpacifico/Chocolatine-14B-Instruct-DPO-v1.2
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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/jpacifico__Chocolatine-14B-Instruct-DPO-v1.2-details.FINGU-AI__Chocolatine-Fusion-14B-details
Dataset Card for Evaluation run of FINGU-AI/Chocolatine-Fusion-14B
Dataset automatically created during the evaluation run of model FINGU-AI/Chocolatine-Fusion-14B
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/FINGU-AI__Chocolatine-Fusion-14B-details.jpacifico__Chocolatine-2-14B-Instruct-v2.0.1-details
Dataset Card for Evaluation run of jpacifico/Chocolatine-2-14B-Instruct-v2.0.1
Dataset automatically created during the evaluation run of model jpacifico/Chocolatine-2-14B-Instruct-v2.0.1
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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/jpacifico__Chocolatine-2-14B-Instruct-v2.0.1-details.jpacifico__Chocolatine-3B-Instruct-DPO-Revised-details
Dataset Card for Evaluation run of jpacifico/Chocolatine-3B-Instruct-DPO-Revised
Dataset automatically created during the evaluation run of model jpacifico/Chocolatine-3B-Instruct-DPO-Revised
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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/jpacifico__Chocolatine-3B-Instruct-DPO-Revised-details.jpacifico__Chocolatine-14B-Instruct-DPO-v1.3-details
Dataset Card for Evaluation run of jpacifico/Chocolatine-14B-Instruct-DPO-v1.3
Dataset automatically created during the evaluation run of model jpacifico/Chocolatine-14B-Instruct-DPO-v1.3
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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/jpacifico__Chocolatine-14B-Instruct-DPO-v1.3-details.jpacifico__Chocolatine-2-14B-Instruct-v2.0b2-details
Dataset Card for Evaluation run of jpacifico/Chocolatine-2-14B-Instruct-v2.0b2
Dataset automatically created during the evaluation run of model jpacifico/Chocolatine-2-14B-Instruct-v2.0b2
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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/jpacifico__Chocolatine-2-14B-Instruct-v2.0b2-details.jpacifico__Chocolatine-2-14B-Instruct-v2.0-details
Dataset Card for Evaluation run of jpacifico/Chocolatine-2-14B-Instruct-v2.0
Dataset automatically created during the evaluation run of model jpacifico/Chocolatine-2-14B-Instruct-v2.0
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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/jpacifico__Chocolatine-2-14B-Instruct-v2.0-details.allknowingroger__Chocolatine-24B-details
Dataset Card for Evaluation run of allknowingroger/Chocolatine-24B
Dataset automatically created during the evaluation run of model allknowingroger/Chocolatine-24B
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__Chocolatine-24B-details.jpacifico__Chocolatine-2-14B-Instruct-v2.0b3-details
Dataset Card for Evaluation run of jpacifico/Chocolatine-2-14B-Instruct-v2.0b3
Dataset automatically created during the evaluation run of model jpacifico/Chocolatine-2-14B-Instruct-v2.0b3
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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/jpacifico__Chocolatine-2-14B-Instruct-v2.0b3-details.Etherll__Chocolatine-3B-Instruct-DPO-Revised-Ties-details
Dataset Card for Evaluation run of Etherll/Chocolatine-3B-Instruct-DPO-Revised-Ties
Dataset automatically created during the evaluation run of model Etherll/Chocolatine-3B-Instruct-DPO-Revised-Ties
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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/Etherll__Chocolatine-3B-Instruct-DPO-Revised-Ties-details.jpacifico__Chocolatine-2-14B-Instruct-DPO-v2.0b1-details
Dataset Card for Evaluation run of jpacifico/Chocolatine-2-14B-Instruct-DPO-v2.0b1
Dataset automatically created during the evaluation run of model jpacifico/Chocolatine-2-14B-Instruct-DPO-v2.0b1
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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/jpacifico__Chocolatine-2-14B-Instruct-DPO-v2.0b1-details.jpacifico__Chocolatine-2-14B-Instruct-v2.0.3-details
Dataset Card for Evaluation run of jpacifico/Chocolatine-2-14B-Instruct-v2.0.3
Dataset automatically created during the evaluation run of model jpacifico/Chocolatine-2-14B-Instruct-v2.0.3
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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/jpacifico__Chocolatine-2-14B-Instruct-v2.0.3-details.Etherll__Chocolatine-3B-Instruct-DPO-Revised-Ties-v2-details
Dataset Card for Evaluation run of Etherll/Chocolatine-3B-Instruct-DPO-Revised-Ties-v2
Dataset automatically created during the evaluation run of model Etherll/Chocolatine-3B-Instruct-DPO-Revised-Ties-v2
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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/Etherll__Chocolatine-3B-Instruct-DPO-Revised-Ties-v2-details.jpacifico__Chocolatine-8B-Instruct-DPO-v1.0-details
Dataset Card for Evaluation run of jpacifico/Chocolatine-8B-Instruct-DPO-v1.0
Dataset automatically created during the evaluation run of model jpacifico/Chocolatine-8B-Instruct-DPO-v1.0
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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/jpacifico__Chocolatine-8B-Instruct-DPO-v1.0-details.