datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
details_alignment-handbook__zephyr-7b-sft-full
Dataset Card for Evaluation run of alignment-handbook/zephyr-7b-sft-full
Dataset automatically created during the evaluation run of model alignment-handbook/zephyr-7b-sft-full 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_alignment-handbook__zephyr-7b-sft-full.details_alignment-handbook__zephyr-7b-dpo-full
Dataset Card for Evaluation run of alignment-handbook/zephyr-7b-dpo-full
Dataset automatically created during the evaluation run of model alignment-handbook/zephyr-7b-dpo-full 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_alignment-handbook__zephyr-7b-dpo-full.details_Amu__dpo-Qwen1.5-0.5B-Chat-alignment-handbookdetails_ewqr2130__alignment-handbook-zephyr-7b_ppo_5e7step_102
Dataset Card for Evaluation run of ewqr2130/alignment-handbook-zephyr-7b_ppo_5e7step_102
Dataset automatically created during the evaluation run of model ewqr2130/alignment-handbook-zephyr-7b_ppo_5e7step_102 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_ewqr2130__alignment-handbook-zephyr-7b_ppo_5e7step_102.details_ewqr2130__alignment-handbook-zephyr-7b-sft-full-dpo-5e7-cont2
Dataset Card for Evaluation run of ewqr2130/alignment-handbook-zephyr-7b-sft-full-dpo-5e7-cont2
Dataset automatically created during the evaluation run of model ewqr2130/alignment-handbook-zephyr-7b-sft-full-dpo-5e7-cont2 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_ewqr2130__alignment-handbook-zephyr-7b-sft-full-dpo-5e7-cont2.details_ewqr2130__alignment-handbook-zephyr-7b_ppo_5e7step_51
Dataset Card for Evaluation run of ewqr2130/alignment-handbook-zephyr-7b_ppo_5e7step_51
Dataset automatically created during the evaluation run of model ewqr2130/alignment-handbook-zephyr-7b_ppo_5e7step_51 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_ewqr2130__alignment-handbook-zephyr-7b_ppo_5e7step_51.details_ewqr2130__alignment-handbook-zephyr-7b-sft-full-dpo-5e7-cont1
Dataset Card for Evaluation run of ewqr2130/alignment-handbook-zephyr-7b-sft-full-dpo-5e7-cont1
Dataset automatically created during the evaluation run of model ewqr2130/alignment-handbook-zephyr-7b-sft-full-dpo-5e7-cont1 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_ewqr2130__alignment-handbook-zephyr-7b-sft-full-dpo-5e7-cont1.details_alignment-handbook__zephyr-7b-dpo-qlora
Dataset Card for Evaluation run of alignment-handbook/zephyr-7b-dpo-qlora
Dataset automatically created during the evaluation run of model alignment-handbook/zephyr-7b-dpo-qlora 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_alignment-handbook__zephyr-7b-dpo-qlora.details_ewqr2130__alignment-handbook-zephyr-7b_ppostep_100
Dataset Card for Evaluation run of ewqr2130/alignment-handbook-zephyr-7b_ppostep_100
Dataset automatically created during the evaluation run of model ewqr2130/alignment-handbook-zephyr-7b_ppostep_100 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_ewqr2130__alignment-handbook-zephyr-7b_ppostep_100.details_alignment-handbook__zephyr-7b-sft-qlora
Dataset Card for Evaluation run of alignment-handbook/zephyr-7b-sft-qlora
Dataset automatically created during the evaluation run of model alignment-handbook/zephyr-7b-sft-qlora 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_alignment-handbook__zephyr-7b-sft-qlora.details_alvarobartt__mistral-7b-orpo-alignment-handbookalpaca52k-alignment-handbook