datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
LongChat-Lines
Dataset Card for "LongChat-Lines"
This dataset is was used to evaluate the performance of model finetuned to operate on longer contexts. It is based on
a task template proposed by LMSys to evaluate attention to arbitrary points in the context. See the full details at
https;//github.com/abacusai/Long-Context.
details_abacusai__bigyi-15b
Dataset Card for Evaluation run of abacusai/bigyi-15b
Dataset automatically created during the evaluation run of model abacusai/bigyi-15b.
The dataset is composed of 136 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.
An additional… See the full description on the dataset page: https://huggingface.co/datasets/OALL/details_abacusai__bigyi-15b.details_abacusai__Smaug-72B-v0.1
Dataset Card for Evaluation run of abacusai/Smaug-72B-v0.1
Dataset automatically created during the evaluation run of model abacusai/Smaug-72B-v0.1.
The dataset is composed of 136 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.
An additional… See the full description on the dataset page: https://huggingface.co/datasets/OALL/details_abacusai__Smaug-72B-v0.1.abacusai__Dracarys-72B-Instruct-details
Dataset Card for Evaluation run of abacusai/Dracarys-72B-Instruct
Dataset automatically created during the evaluation run of model abacusai/Dracarys-72B-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/abacusai__Dracarys-72B-Instruct-details.abacusai__Llama-3-Smaug-8B-details
Dataset Card for Evaluation run of abacusai/Llama-3-Smaug-8B
Dataset automatically created during the evaluation run of model abacusai/Llama-3-Smaug-8B
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/abacusai__Llama-3-Smaug-8B-details.details_abacusai__Slerp-CM-mist-dpo
Dataset Card for Evaluation run of abacusai/Slerp-CM-mist-dpo
Dataset automatically created during the evaluation run of model abacusai/Slerp-CM-mist-dpo.
The dataset is composed of 136 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.
An… See the full description on the dataset page: https://huggingface.co/datasets/OALL/details_abacusai__Slerp-CM-mist-dpo.details_abacusai__Smaug-Llama-3-70B-Instruct
Dataset Card for Evaluation run of abacusai/Smaug-Llama-3-70B-Instruct
Dataset automatically created during the evaluation run of model abacusai/Smaug-Llama-3-70B-Instruct.
The dataset is composed of 136 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… See the full description on the dataset page: https://huggingface.co/datasets/OALL/details_abacusai__Smaug-Llama-3-70B-Instruct.abacusai__Smaug-72B-v0.1-details
Dataset Card for Evaluation run of abacusai/Smaug-72B-v0.1
Dataset automatically created during the evaluation run of model abacusai/Smaug-72B-v0.1
The dataset is composed of 44 configuration(s), each one corresponding 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 latest results.
An additional… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/abacusai__Smaug-72B-v0.1-details.abacusai__Smaug-Llama-3-70B-Instruct-32K-details
Dataset Card for Evaluation run of abacusai/Smaug-Llama-3-70B-Instruct-32K
Dataset automatically created during the evaluation run of model abacusai/Smaug-Llama-3-70B-Instruct-32K
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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/abacusai__Smaug-Llama-3-70B-Instruct-32K-details.abacusai__Smaug-Mixtral-v0.1-details
Dataset Card for Evaluation run of abacusai/Smaug-Mixtral-v0.1
Dataset automatically created during the evaluation run of model abacusai/Smaug-Mixtral-v0.1
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 pointing to the latest results.
An… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/abacusai__Smaug-Mixtral-v0.1-details.abacusai__bigstral-12b-32k-details
Dataset Card for Evaluation run of abacusai/bigstral-12b-32k
Dataset automatically created during the evaluation run of model abacusai/bigstral-12b-32k
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/abacusai__bigstral-12b-32k-details.abacusai__Smaug-Qwen2-72B-Instruct-details
Dataset Card for Evaluation run of abacusai/Smaug-Qwen2-72B-Instruct
Dataset automatically created during the evaluation run of model abacusai/Smaug-Qwen2-72B-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/abacusai__Smaug-Qwen2-72B-Instruct-details.abacusai__Smaug-34B-v0.1-details
Dataset Card for Evaluation run of abacusai/Smaug-34B-v0.1
Dataset automatically created during the evaluation run of model abacusai/Smaug-34B-v0.1
The dataset is composed of 44 configuration(s), each one corresponding 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 latest results.
An additional… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/abacusai__Smaug-34B-v0.1-details.abacusai__Liberated-Qwen1.5-14B-details
Dataset Card for Evaluation run of abacusai/Liberated-Qwen1.5-14B
Dataset automatically created during the evaluation run of model abacusai/Liberated-Qwen1.5-14B
The dataset is composed of 38 configuration(s), each one corresponding 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 latest results.… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/abacusai__Liberated-Qwen1.5-14B-details.details_abacusai__Liberated-Qwen1.5-14B
Dataset Card for Evaluation run of abacusai/Liberated-Qwen1.5-14B
Dataset automatically created during the evaluation run of model abacusai/Liberated-Qwen1.5-14B.
The dataset is composed of 136 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.
An… See the full description on the dataset page: https://huggingface.co/datasets/OALL/details_abacusai__Liberated-Qwen1.5-14B.abacusai__bigyi-15b-details
Dataset Card for Evaluation run of abacusai/bigyi-15b
Dataset automatically created during the evaluation run of model abacusai/bigyi-15b
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/abacusai__bigyi-15b-details.details_abacusai__Smaug-Llama-3-70B-Instruct-32K
Dataset Card for Evaluation run of abacusai/Smaug-Llama-3-70B-Instruct-32K
Dataset automatically created during the evaluation run of model abacusai/Smaug-Llama-3-70B-Instruct-32K.
The dataset is composed of 136 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/OALL/details_abacusai__Smaug-Llama-3-70B-Instruct-32K.abacusai__Smaug-Qwen2-72B-Instructdetails_abacusai__Smaug-Mixtral-v0.1
Dataset Card for Evaluation run of abacusai/Smaug-Mixtral-v0.1
Dataset automatically created during the evaluation run of model abacusai/Smaug-Mixtral-v0.1.
The dataset is composed of 136 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.
An… See the full description on the dataset page: https://huggingface.co/datasets/OALL/details_abacusai__Smaug-Mixtral-v0.1.details_abacusai__Smaug-Qwen2-72B-Instruct
Dataset Card for Evaluation run of abacusai/Smaug-Qwen2-72B-Instruct
Dataset automatically created during the evaluation run of model abacusai/Smaug-Qwen2-72B-Instruct.
The dataset is composed of 136 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… See the full description on the dataset page: https://huggingface.co/datasets/OALL/details_abacusai__Smaug-Qwen2-72B-Instruct.details_abacusai__Dracarys-72B-Instruct
Dataset Card for Evaluation run of abacusai/Dracarys-72B-Instruct
Dataset automatically created during the evaluation run of model abacusai/Dracarys-72B-Instruct.
The dataset is composed of 136 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.
An… See the full description on the dataset page: https://huggingface.co/datasets/OALL/details_abacusai__Dracarys-72B-Instruct.details_abacusai__bigstral-12b-32k
Dataset Card for Evaluation run of abacusai/bigstral-12b-32k
Dataset automatically created during the evaluation run of model abacusai/bigstral-12b-32k.
The dataset is composed of 136 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.
An… See the full description on the dataset page: https://huggingface.co/datasets/OALL/details_abacusai__bigstral-12b-32k.abacusai__Smaug-Llama-3-70B-Instruct-32Kabacusai__Smaug-34B-v0.1abacusai__Smaug-Mixtral-v0.1details_abacusai__Smaug-34B-v0.1
Dataset Card for Evaluation run of abacusai/Smaug-34B-v0.1
Dataset automatically created during the evaluation run of model abacusai/Smaug-34B-v0.1.
The dataset is composed of 136 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 latest results.
An additional… See the full description on the dataset page: https://huggingface.co/datasets/OALL/details_abacusai__Smaug-34B-v0.1.