datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
rys-sovereign-collection-v2
RYS Sovereign Collection v2 — Cross-architecture Sweep Corpus
Layer-duplication ("Repeat Your Self") sweep results across 21 model variants spanning 10 architecture families, 135M to 32B parameters. No training. No new weights. The corpus is the sweep JSONLs and the analysis script that reads them.
Authors: John Broadway, with collaboration from Claude (Opus 4.6 in April 2026 v1 build; Opus 4.7 in May 2026 v2 analysis and publication). Original RYS method by David Ng on Qwen2-72B;… See the full description on the dataset page: https://huggingface.co/datasets/john-broadway/rys-sovereign-collection-v2.dnhkng__RYS-XLarge-details
Dataset Card for Evaluation run of dnhkng/RYS-XLarge
Dataset automatically created during the evaluation run of model dnhkng/RYS-XLarge
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/dnhkng__RYS-XLarge-details.MaziyarPanahi__calme-2.2-rys-78b-details
Dataset Card for Evaluation run of MaziyarPanahi/calme-2.2-rys-78b
Dataset automatically created during the evaluation run of model MaziyarPanahi/calme-2.2-rys-78b
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/MaziyarPanahi__calme-2.2-rys-78b-details.MaziyarPanahi__calme-2.1-rys-78b-details
Dataset Card for Evaluation run of MaziyarPanahi/calme-2.1-rys-78b
Dataset automatically created during the evaluation run of model MaziyarPanahi/calme-2.1-rys-78b
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/MaziyarPanahi__calme-2.1-rys-78b-details.MaziyarPanahi__calme-2.4-rys-78b-details
Dataset Card for Evaluation run of MaziyarPanahi/calme-2.4-rys-78b
Dataset automatically created during the evaluation run of model MaziyarPanahi/calme-2.4-rys-78b
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/MaziyarPanahi__calme-2.4-rys-78b-details.dnhkng__RYS-Llama-3-Huge-Instruct-details
Dataset Card for Evaluation run of dnhkng/RYS-Llama-3-Huge-Instruct
Dataset automatically created during the evaluation run of model dnhkng/RYS-Llama-3-Huge-Instruct
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/dnhkng__RYS-Llama-3-Huge-Instruct-details.dnhkng__RYS-XLarge-base-details
Dataset Card for Evaluation run of dnhkng/RYS-XLarge-base
Dataset automatically created during the evaluation run of model dnhkng/RYS-XLarge-base
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/dnhkng__RYS-XLarge-base-details.dnhkng__RYS-Llama3.1-Large-details
Dataset Card for Evaluation run of dnhkng/RYS-Llama3.1-Large
Dataset automatically created during the evaluation run of model dnhkng/RYS-Llama3.1-Large
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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/dnhkng__RYS-Llama3.1-Large-details.MaziyarPanahi__calme-2.3-rys-78b-details
Dataset Card for Evaluation run of MaziyarPanahi/calme-2.3-rys-78b
Dataset automatically created during the evaluation run of model MaziyarPanahi/calme-2.3-rys-78b
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/MaziyarPanahi__calme-2.3-rys-78b-details.dnhkng__RYS-Phi-3-medium-4k-instruct-details
Dataset Card for Evaluation run of dnhkng/RYS-Phi-3-medium-4k-instruct
Dataset automatically created during the evaluation run of model dnhkng/RYS-Phi-3-medium-4k-instruct
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/dnhkng__RYS-Phi-3-medium-4k-instruct-details.dnhkng__RYS-Huge-bnb-4bit-details
Dataset Card for Evaluation run of dnhkng/RYS-Huge-bnb-4bit
Dataset automatically created during the evaluation run of model dnhkng/RYS-Huge-bnb-4bit
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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/dnhkng__RYS-Huge-bnb-4bit-details.dnhkng__RYS-XLarge2-details
Dataset Card for Evaluation run of dnhkng/RYS-XLarge2
Dataset automatically created during the evaluation run of model dnhkng/RYS-XLarge2
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/dnhkng__RYS-XLarge2-details.dnhkng__RYS-Llama-3-Large-Instruct-details
Dataset Card for Evaluation run of dnhkng/RYS-Llama-3-Large-Instruct
Dataset automatically created during the evaluation run of model dnhkng/RYS-Llama-3-Large-Instruct
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/dnhkng__RYS-Llama-3-Large-Instruct-details.dnhkng__RYS-Medium-details
Dataset Card for Evaluation run of dnhkng/RYS-Medium
Dataset automatically created during the evaluation run of model dnhkng/RYS-Medium
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/dnhkng__RYS-Medium-details.dnhkng__RYS-Llama-3.1-8B-Instruct-details
Dataset Card for Evaluation run of dnhkng/RYS-Llama-3.1-8B-Instruct
Dataset automatically created during the evaluation run of model dnhkng/RYS-Llama-3.1-8B-Instruct
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/dnhkng__RYS-Llama-3.1-8B-Instruct-details.RysMtxuRxZROvY39dnhkng__RYS-Llama-3-8B-Instruct-details
Dataset Card for Evaluation run of dnhkng/RYS-Llama-3-8B-Instruct
Dataset automatically created during the evaluation run of model dnhkng/RYS-Llama-3-8B-Instruct
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.… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/dnhkng__RYS-Llama-3-8B-Instruct-details.