datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
AA_preference_vicuna-13b_l0_cutAA_preference_vicuna-13b_cosi_cutAA_preference_vicuna-13b_l0_fullAA_preference_vicuna-13b_cooccur_fullAA_preference_vicuna-13b_cosi_fulllm-eval-results-yunconglong-DARE_TIES_13B-private
Dataset Card for Evaluation run of yunconglong/DARE_TIES_13B
Dataset automatically created during the evaluation run of model yunconglong/DARE_TIES_13B
The dataset is composed of 62 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/nyu-dice-lab/lm-eval-results-yunconglong-DARE_TIES_13B-private.details_core42__jais-13b
Dataset Card for Evaluation run of core42/jais-13b
Dataset automatically created during the evaluation run of model core42/jais-13b.
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 configuration… See the full description on the dataset page: https://huggingface.co/datasets/OALL/details_core42__jais-13b.lm-eval-results-yunconglong-Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B-private
Dataset Card for Evaluation run of yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B
Dataset automatically created during the evaluation run of model yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B
The dataset is composed of 62 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"… See the full description on the dataset page: https://huggingface.co/datasets/nyu-dice-lab/lm-eval-results-yunconglong-Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B-private.details_core42__jais-13b-chat
Dataset Card for Evaluation run of core42/jais-13b-chat
Dataset automatically created during the evaluation run of model core42/jais-13b-chat.
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_core42__jais-13b-chat.details_FreedomIntelligence__AceGPT-v1.5-13B-Chat
Dataset Card for Evaluation run of FreedomIntelligence/AceGPT-v1.5-13B-Chat
Dataset automatically created during the evaluation run of model FreedomIntelligence/AceGPT-v1.5-13B-Chat.
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… See the full description on the dataset page: https://huggingface.co/datasets/OALL/details_FreedomIntelligence__AceGPT-v1.5-13B-Chat.details_yunconglong__DARE_TIES_13B
Dataset Card for Evaluation run of yunconglong/DARE_TIES_13B
Dataset automatically created during the evaluation run of model yunconglong/DARE_TIES_13B.
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_yunconglong__DARE_TIES_13B.details_FreedomIntelligence__AceGPT-13B-chat
Dataset Card for Evaluation run of FreedomIntelligence/AceGPT-13B-chat
Dataset automatically created during the evaluation run of model FreedomIntelligence/AceGPT-13B-chat.
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_FreedomIntelligence__AceGPT-13B-chat.details_haoranxu__ALMA-13B-R
Dataset Card for Evaluation run of haoranxu/ALMA-13B-R
Dataset automatically created during the evaluation run of model haoranxu/ALMA-13B-R.
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_haoranxu__ALMA-13B-R.details_FreedomIntelligence__AceGPT-13B
Dataset Card for Evaluation run of FreedomIntelligence/AceGPT-13B
Dataset automatically created during the evaluation run of model FreedomIntelligence/AceGPT-13B.
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_FreedomIntelligence__AceGPT-13B.lm-eval-results-yunconglong-MoE_13B_DPO-private
Dataset Card for Evaluation run of yunconglong/MoE_13B_DPO
Dataset automatically created during the evaluation run of model yunconglong/MoE_13B_DPO
The dataset is composed of 62 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/nyu-dice-lab/lm-eval-results-yunconglong-MoE_13B_DPO-private.olmo-2-1124-13b-preference-mix-mechanicalolmo-2-1124-13b-preference-mix
OLMo 2 1124 13B Preference Mixture
Note that this collection is licensed under ODC-BY-1.0 license; different licenses apply to subsets of the data. Some portions of the dataset are non-commercial. We present the mixture as a research artifact.
This mix is made up of the following on-policy preference datasets generated using a synthetic data generation pipeline similar to Tulu
Reused prompts from the SFT mix (via ai2-adapt-dev/sft_v3.9_used_on_policy_po_olmo2_13b and… See the full description on the dataset page: https://huggingface.co/datasets/allenai/olmo-2-1124-13b-preference-mix.bioasq-rag-13b-resplit
BioASQ RAG 13B (Resplit)
Reshuffled version of DinoStackAI/bioasq-rag-13b for Retrieval-Augmented Generation (RAG).
All original train, dev and test queries were merged, shuffled with seed 42, and reassigned using:
0.2 of all queries → test
0.2 of the remaining queries → dev
the rest → train
The shared PubMed corpus is unchanged from the source dataset.
Structure
Subset
Splits
Description
corpus
train (default)
PubMed abstracts shared across all query… See the full description on the dataset page: https://huggingface.co/datasets/DinoStackAI/bioasq-rag-13b-resplit.olmo-2-1124-13b-preference-mix-leetspeakreward-bench-Llama-2-13b-chat-hf-yes-nolm-eval-results-RubielLabarta-LogoS-7Bx2-MoE-13B-v0.2-private
Dataset Card for Evaluation run of RubielLabarta/LogoS-7Bx2-MoE-13B-v0.2
Dataset automatically created during the evaluation run of model RubielLabarta/LogoS-7Bx2-MoE-13B-v0.2
The dataset is composed of 62 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… See the full description on the dataset page: https://huggingface.co/datasets/nyu-dice-lab/lm-eval-results-RubielLabarta-LogoS-7Bx2-MoE-13B-v0.2-private.reward-bench-Llama-2-13b-hf-yes-noolmo-2-1124-13b-preference-mix-randomcasedetails_meta-llama__Llama-2-13b-hf
Dataset Card for Evaluation run of meta-llama/Llama-2-13b-hf
Dataset automatically created during the evaluation run of model meta-llama/Llama-2-13b-hf.
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_meta-llama__Llama-2-13b-hf.details_FreedomIntelligence__AceGPT-v1.5-13B
Dataset Card for Evaluation run of FreedomIntelligence/AceGPT-v1.5-13B
Dataset automatically created during the evaluation run of model FreedomIntelligence/AceGPT-v1.5-13B.
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_FreedomIntelligence__AceGPT-v1.5-13B.huggyllama__llama-13b-details
Dataset Card for Evaluation run of huggyllama/llama-13b
Dataset automatically created during the evaluation run of model huggyllama/llama-13b
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/huggyllama__llama-13b-details.llava-vicuna13b-SAEfactprobe-replication-generation-spouse-13b-base-v1
factprobe-replication-generation-spouse-13b-base-v1
Free-form spouse generation: for every P26 subject NAME form, the base model was asked 'Who is the {spouse} of ? Answer with just the name:' with 4 in-context demos, and sampled 5 times with nucleus sampling (top_p=0.95, temperature=1.0, max_tokens=64, stop at newline). 28,815 subject names. Companion to the P(Yes) probing datasets — this is what the model GENERATES, not a yes/no score.
Dataset Info
Rows: 30796… See the full description on the dataset page: https://huggingface.co/datasets/latkes/factprobe-replication-generation-spouse-13b-base-v1.llava-vicuna13b-SAE-Vllm-as-judge-generations-OLMo-2-1124-13B-Instruct