datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
tinyevals-logprobs-llama2-allsizesllama2_QA_Economics_230915
Dataset Card for "llama2_QA_Economics_230915"
More Information needed
llama2-high-entropy-prompts
High-entropy prompts for suffix-based backdoor detection
Prompts on which base meta-llama/Llama-2-7b-hf has high predictive
entropy, built to give a suffix-optimization backdoor detector measurable
headroom: a clean model should stay uncertain on these prompts, while a poisoned
model driven by a trigger-like suffix should collapse to low entropy. Prompts
where the base model is already confident cannot separate the two.
How the prompts were made
Short prefixes… See the full description on the dataset page: https://huggingface.co/datasets/Alookhoshk/llama2-high-entropy-prompts.llama2_7b_chat-boolq
Dataset Card for "llama2_7b_chat-boolq"
More Information needed
nuzzle-scan-saraprice-llama2-7b-backdoor-deploymentllama-2-optimized-product-titles-esci-4-7-temp
Dataset Card for "llama-2-optimized-product-titles-esci-4-7-temp"
More Information needed
judged_wj_ah_llama2_passed_only_w_llama_outputllama_2_product_titles-esci_train-temp-pos
Dataset Card for "llama_2_product_titles-esci_train-temp-pos"
More Information needed
llama_2_optimized_product_titles-esci-test-sft
Dataset Card for "llama_2_optimized_product_titles-esci-test-sft"
More Information needed
wj_ah_ASR_w_llama2_hs_w_op_kmeans_k12llama_2-product-titles-esci-test-temp
Dataset Card for "llama_2-product-titles-esci-test-temp"
More Information needed
llama-2-optimized-product-titles-esci-test-sft-temp
Dataset Card for "llama-2-optimized-product-titles-esci-test-sft-temp"
More Information needed
cg-llama2-1k
Dataset Card for "cg-llama2-1k"
More Information needed
llama2_7b_chat-siqaLlama2TestingAmazonReviewjudged_wj_ah_llama2wj_ah_ASR_w_llama2_hs_w_opllama_2-optimized-titles-esci-sft-test
Dataset Card for "llama_2-optimized-titles-esci-sft-test"
More Information needed
judged_wj_ah_llama2_passed_onlywj_ah_ASR_w_llama2_hs_w_op_capped100_recluster_k7mmlu_llama2_7b_mistral_7b_prompt_lossesllama_2-product-titles-esci-test-sft-temp
Dataset Card for "llama_2-product-titles-esci-test-sft-temp"
More Information needed
arc_llama2_7b_mistral_7b_prompt_lossesskymizer__Llama2-7b-sft-chat-custom-template-dpo-details
Dataset Card for Evaluation run of skymizer/Llama2-7b-sft-chat-custom-template-dpo
Dataset automatically created during the evaluation run of model skymizer/Llama2-7b-sft-chat-custom-template-dpo
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/skymizer__Llama2-7b-sft-chat-custom-template-dpo-details.llama_2-product-titles-esci-train-all-temp
Dataset Card for "llama_2-product-titles-esci-train-all-temp"
More Information needed
llama_2-product-titles-esci-sft-train
Dataset Card for "llama_2-product-titles-esci-sft-train"
More Information needed
sabersaleh__Llama2-7B-KTO-details
Dataset Card for Evaluation run of sabersaleh/Llama2-7B-KTO
Dataset automatically created during the evaluation run of model sabersaleh/Llama2-7B-KTO
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.
An… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/sabersaleh__Llama2-7B-KTO-details.sabersaleh__Llama2-7B-SimPO-details
Dataset Card for Evaluation run of sabersaleh/Llama2-7B-SimPO
Dataset automatically created during the evaluation run of model sabersaleh/Llama2-7B-SimPO
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/sabersaleh__Llama2-7B-SimPO-details.mmlu_llama2_7b_mistral_7bllama_2_optimized_product_titles-esci-test
Dataset Card for "llama_2_optimized_product_titles-esci-test"
More Information needed
