datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
Llama-2-7b-KronQ-HG
Llama-2-7b — KronQ H_G (output-side gradient covariance)
Paper: arXiv:2607.07964 · Code: GitHub
Pre-computed H_G for Llama-2-7b, the output-side curvature factor used by KronQ under the K-FAC factorization H ≈ H_X ⊗ H_G. H_G is the per-sublayer sampled-Fisher gradient covariance (labels drawn from the model distribution) (E[g gᵀ] over the layer output), distinct from the standard input-side Hessian H_X (which GPTQ/GPTAQ build online during calibration).
Publishing this lets you… See the full description on the dataset page: https://huggingface.co/datasets/donghyunli/Llama-2-7b-KronQ-HG.llama2_7b_chat-boolq-results
Dataset Card for "llama2_7b_chat-boolq-results"
More Information needed
llama2_7b_chat-piqa-resultsdetails_Azure99__blossom-v2-llama2-7b
Dataset Card for Evaluation run of Azure99/blossom-v2-llama2-7b
Dataset Summary
Dataset automatically created during the evaluation run of model Azure99/blossom-v2-llama2-7b on the Open LLM Leaderboard.
The dataset is composed of 64 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_Azure99__blossom-v2-llama2-7b.llama2_7b_chat-siqa-resultsdetails_itsliupeng__llama2_7b_code
Dataset Card for Evaluation run of itsliupeng/llama2_7b_code
Dataset Summary
Dataset automatically created during the evaluation run of model itsliupeng/llama2_7b_code on the Open LLM Leaderboard.
The dataset is composed of 64 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_itsliupeng__llama2_7b_code.IO_callib_pairs_Llama2_7bdetails_georgesung__llama2_7b_chat_uncensored
Dataset Card for Evaluation run of georgesung/llama2_7b_chat_uncensored
Dataset Summary
Dataset automatically created during the evaluation run of model georgesung/llama2_7b_chat_uncensored on the Open LLM Leaderboard.
The dataset is composed of 64 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_georgesung__llama2_7b_chat_uncensored.details_mncai__Llama2-7B-guanaco-dolphin-500
Dataset Card for Evaluation run of mncai/Llama2-7B-guanaco-dolphin-500
Dataset automatically created during the evaluation run of model mncai/Llama2-7B-guanaco-dolphin-500 on the Open LLM Leaderboard.
The dataset is composed of 64 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_mncai__Llama2-7B-guanaco-dolphin-500.details_beaugogh__Llama2-7b-openorca-mc-v2-dpo
Dataset Card for Evaluation run of beaugogh/Llama2-7b-openorca-mc-v2-dpo
Dataset Summary
Dataset automatically created during the evaluation run of model beaugogh/Llama2-7b-openorca-mc-v2-dpo on the Open LLM Leaderboard.
The dataset is composed of 64 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_beaugogh__Llama2-7b-openorca-mc-v2-dpo.details_Shengkun__LLama2-7B-Structural-Prune-1.2xdetails_TinyPixel__llama2-7b-instruct
Dataset Card for Evaluation run of TinyPixel/llama2-7b-instruct
Dataset Summary
Dataset automatically created during the evaluation run of model TinyPixel/llama2-7b-instruct on the Open LLM Leaderboard.
The dataset is composed of 61 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_TinyPixel__llama2-7b-instruct.details_l3utterfly__llama2-7b-layla
Dataset Card for Evaluation run of l3utterfly/llama2-7b-layla
Dataset Summary
Dataset automatically created during the evaluation run of model l3utterfly/llama2-7b-layla on the Open LLM Leaderboard.
The dataset is composed of 64 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_l3utterfly__llama2-7b-layla.details_Telugu-LLM-Labs__Telugu-Llama2-7B-v0-Instruct
Dataset Card for Evaluation run of Telugu-LLM-Labs/Telugu-Llama2-7B-v0-Instruct
Dataset automatically created during the evaluation run of model Telugu-LLM-Labs/Telugu-Llama2-7B-v0-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 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_Telugu-LLM-Labs__Telugu-Llama2-7B-v0-Instruct.details_JCX-kcuf__Llama-2-7b-hf-llama2-chat-80k
Dataset Card for Evaluation run of JCX-kcuf/Llama-2-7b-hf-llama2-chat-80k
Dataset automatically created during the evaluation run of model JCX-kcuf/Llama-2-7b-hf-llama2-chat-80k 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_JCX-kcuf__Llama-2-7b-hf-llama2-chat-80k.details_ehartford__dolphin-llama2-7b
Dataset Card for Evaluation run of ehartford/dolphin-llama2-7b
Dataset Summary
Dataset automatically created during the evaluation run of model ehartford/dolphin-llama2-7b on the Open LLM Leaderboard.
The dataset is composed of 64 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_ehartford__dolphin-llama2-7b.data_llama2_7b_new_1details_beaugogh__Llama2-7b-sharegpt4
Dataset Card for Evaluation run of beaugogh/Llama2-7b-sharegpt4
Dataset Summary
Dataset automatically created during the evaluation run of model beaugogh/Llama2-7b-sharegpt4 on the Open LLM Leaderboard.
The dataset is composed of 64 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_beaugogh__Llama2-7b-sharegpt4.details_itsliupeng__llama2_7b_mmlu
Dataset Card for Evaluation run of itsliupeng/llama2_7b_mmlu
Dataset Summary
Dataset automatically created during the evaluation run of model itsliupeng/llama2_7b_mmlu on the Open LLM Leaderboard.
The dataset is composed of 64 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_itsliupeng__llama2_7b_mmlu.details_selfrag__selfrag_llama2_7b
Dataset Card for Evaluation run of selfrag/selfrag_llama2_7b
Dataset automatically created during the evaluation run of model selfrag/selfrag_llama2_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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_selfrag__selfrag_llama2_7b.details_lvkaokao__llama2-7b-hf-instruction-lora
Dataset Card for Evaluation run of lvkaokao/llama2-7b-hf-instruction-lora
Dataset Summary
Dataset automatically created during the evaluation run of model lvkaokao/llama2-7b-hf-instruction-lora on the Open LLM Leaderboard.
The dataset is composed of 64 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_lvkaokao__llama2-7b-hf-instruction-lora.details_davzoku__cria-llama2-7b-v1.3
Dataset Card for Evaluation run of davzoku/cria-llama2-7b-v1.3
Dataset Summary
Dataset automatically created during the evaluation run of model davzoku/cria-llama2-7b-v1.3 on the Open LLM Leaderboard.
The dataset is composed of 64 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_davzoku__cria-llama2-7b-v1.3.details_rombodawg__LosslessMegaCoder-llama2-7b-mini
Dataset Card for Evaluation run of rombodawg/LosslessMegaCoder-llama2-7b-mini
Dataset Summary
Dataset automatically created during the evaluation run of model rombodawg/LosslessMegaCoder-llama2-7b-mini on the Open LLM Leaderboard.
The dataset is composed of 64 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_rombodawg__LosslessMegaCoder-llama2-7b-mini.details_YeungNLP__firefly-llama2-7b-pretrain
Dataset Card for Evaluation run of YeungNLP/firefly-llama2-7b-pretrain
Dataset Summary
Dataset automatically created during the evaluation run of model YeungNLP/firefly-llama2-7b-pretrain on the Open LLM Leaderboard.
The dataset is composed of 64 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_YeungNLP__firefly-llama2-7b-pretrain.Alpaca_Analysis_llama2_7b
Dataset Card for "Alpaca_Analysis_llama2_7b"
More Information needed
details_hyunseoki__ko-ref-llama2-7b
Dataset Card for Evaluation run of hyunseoki/ko-ref-llama2-7b
Dataset Summary
Dataset automatically created during the evaluation run of model hyunseoki/ko-ref-llama2-7b on the Open LLM Leaderboard.
The dataset is composed of 64 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_hyunseoki__ko-ref-llama2-7b.details_starmpcc__Asclepius-Llama2-7B
Dataset Card for Evaluation run of starmpcc/Asclepius-Llama2-7B
Dataset Summary
Dataset automatically created during the evaluation run of model starmpcc/Asclepius-Llama2-7B on the Open LLM Leaderboard.
The dataset is composed of 64 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_starmpcc__Asclepius-Llama2-7B.details_bongchoi__test-llama2-7b
Dataset Card for Evaluation run of bongchoi/test-llama2-7b
Dataset Summary
Dataset automatically created during the evaluation run of model bongchoi/test-llama2-7b on the Open LLM Leaderboard.
The dataset is composed of 64 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_bongchoi__test-llama2-7b.Wiz70_Analysis_llama2_7b
Dataset Card for "Wiz70_Analysis_llama2_7b"
More Information needed
details_mncai__Llama2-7B-guanaco-1k
Dataset Card for Evaluation run of mncai/Llama2-7B-guanaco-1k
Dataset Summary
Dataset automatically created during the evaluation run of model mncai/Llama2-7B-guanaco-1k on the Open LLM Leaderboard.
The dataset is composed of 64 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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard-old/details_mncai__Llama2-7B-guanaco-1k.