datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
sokobanlevelslinearizer-minimal-repro
Minimal Repro: "Who Said Neural Networks Aren't Linear?" (the Linearizer, arXiv:2510.08570)
A ~250-line 2D toy that proves the paper's core principle end to end. Not a full-paper reproduction (no LPIPS, no image diffusion, no large-scale training) — just the smallest experiment that demonstrates:
Induced linearity is exact. f(x) = g⁻¹(A·g(x)) satisfies f(a·x+b) = a·f(x) + b·f(0) to machine precision when the identity is evaluated in the space where the algebra happens (g-space)… See the full description on the dataset page: https://huggingface.co/datasets/pngwn/linearizer-minimal-repro.DreadPoor__Promissum_Mane-8B-LINEAR-lorablated-details
Dataset Card for Evaluation run of DreadPoor/Promissum_Mane-8B-LINEAR-lorablated
Dataset automatically created during the evaluation run of model DreadPoor/Promissum_Mane-8B-LINEAR-lorablated
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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/DreadPoor__Promissum_Mane-8B-LINEAR-lorablated-details.open-perfectblend-kimi-linear-regen
Open PerfectBlend Kimi Linear Regen
This dataset regenerates the assistant messages in
mlabonne/open-perfectblend
with Kimi-Linear-48B-A3B-Instruct. It is intended for speculative-decoding
drafter training and related research.
Generation
Source conversation structure and user messages: mlabonne/open-perfectblend
Target model: Kimi-Linear-48B-A3B-Instruct
Temperature: 0.7
Maximum new tokens per assistant turn: 8192
Assistant turns were regenerated sequentially.… See the full description on the dataset page: https://huggingface.co/datasets/Dogacel/open-perfectblend-kimi-linear-regen.repro-finite-and-corruption-robust-regret-bounds-in-online-inverse-linear-optimization-traces
Agent traces
Agent sessions published from a Trackio Logbook.
repro-stochastic-linear-bandits-with-parameter-noise-traces
Agent traces
Agent sessions published from a Trackio Logbook.
repro-softmax-as-linear-attention-in-the-large-prompt-regime-a-measure-based-perspecti-traces
Agent traces
Agent sessions published from a Trackio Logbook.
DreadPoor__BaeZel-8B-LINEAR-details
Dataset Card for Evaluation run of DreadPoor/BaeZel-8B-LINEAR
Dataset automatically created during the evaluation run of model DreadPoor/BaeZel-8B-LINEAR
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/DreadPoor__BaeZel-8B-LINEAR-details.ai-paper-intellectual-lineage-2023
Intellectual Lineage of Impactful AI Research Papers (2023-2024)
Dataset Description
This dataset contains 20 impactful AI research papers published between 2022-2024, along with their intellectual lineage - tracing 1-2 key prior works each paper builds upon, and a ~300-word paragraph explaining the relationship between the current work and its foundations.
Purpose
Understanding how research ideas evolve and build upon prior work is crucial for:
Researchers… See the full description on the dataset page: https://huggingface.co/datasets/AmberLJC/ai-paper-intellectual-lineage-2023.DreadPoor__Promissum_Mane-8B-LINEAR-details
Dataset Card for Evaluation run of DreadPoor/Promissum_Mane-8B-LINEAR
Dataset automatically created during the evaluation run of model DreadPoor/Promissum_Mane-8B-LINEAR
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/DreadPoor__Promissum_Mane-8B-LINEAR-details.DreadPoor__Matryoshka-8B-LINEAR-details
Dataset Card for Evaluation run of DreadPoor/Matryoshka-8B-LINEAR
Dataset automatically created during the evaluation run of model DreadPoor/Matryoshka-8B-LINEAR
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/DreadPoor__Matryoshka-8B-LINEAR-details.DreadPoor__Rusted_Platinum-8B-LINEAR-details
Dataset Card for Evaluation run of DreadPoor/Rusted_Platinum-8B-LINEAR
Dataset automatically created during the evaluation run of model DreadPoor/Rusted_Platinum-8B-LINEAR
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/DreadPoor__Rusted_Platinum-8B-LINEAR-details.DreadPoor__Rusted_Gold-8B-LINEAR-details
Dataset Card for Evaluation run of DreadPoor/Rusted_Gold-8B-LINEAR
Dataset automatically created during the evaluation run of model DreadPoor/Rusted_Gold-8B-LINEAR
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/DreadPoor__Rusted_Gold-8B-LINEAR-details.DreadPoor__Noxis-8B-LINEAR-details
Dataset Card for Evaluation run of DreadPoor/Noxis-8B-LINEAR
Dataset automatically created during the evaluation run of model DreadPoor/Noxis-8B-LINEAR
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/DreadPoor__Noxis-8B-LINEAR-details.overthinker-lineagesDreadPoor__inexpertus_1.1-8B-LINEAR-details
Dataset Card for Evaluation run of DreadPoor/inexpertus_1.1-8B-LINEAR
Dataset automatically created during the evaluation run of model DreadPoor/inexpertus_1.1-8B-LINEAR
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/DreadPoor__inexpertus_1.1-8B-LINEAR-details.DreadPoor__inexpertus_1.2-8B-LINEAR-details
Dataset Card for Evaluation run of DreadPoor/inexpertus_1.2-8B-LINEAR
Dataset automatically created during the evaluation run of model DreadPoor/inexpertus_1.2-8B-LINEAR
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/DreadPoor__inexpertus_1.2-8B-LINEAR-details.DreadPoor__Aurora_faustus-8B-LINEAR-details
Dataset Card for Evaluation run of DreadPoor/Aurora_faustus-8B-LINEAR
Dataset automatically created during the evaluation run of model DreadPoor/Aurora_faustus-8B-LINEAR
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/DreadPoor__Aurora_faustus-8B-LINEAR-details.DreadPoor__Alita99-8B-LINEAR-details
Dataset Card for Evaluation run of DreadPoor/Alita99-8B-LINEAR
Dataset automatically created during the evaluation run of model DreadPoor/Alita99-8B-LINEAR
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/DreadPoor__Alita99-8B-LINEAR-details.DreadPoor__H_the_eighth-8B-LINEAR-details
Dataset Card for Evaluation run of DreadPoor/H_the_eighth-8B-LINEAR
Dataset automatically created during the evaluation run of model DreadPoor/H_the_eighth-8B-LINEAR
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/DreadPoor__H_the_eighth-8B-LINEAR-details.teleportconfigs:
config_name: teleport
data_files:
path: teleport_dataset.jsonl
split: train
DreadPoor__Eunoia_Vespera-8B-LINEAR-details
Dataset Card for Evaluation run of DreadPoor/Eunoia_Vespera-8B-LINEAR
Dataset automatically created during the evaluation run of model DreadPoor/Eunoia_Vespera-8B-LINEAR
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/DreadPoor__Eunoia_Vespera-8B-LINEAR-details.DreadPoor__Damasteel-8B-LINEAR-details
Dataset Card for Evaluation run of DreadPoor/Damasteel-8B-LINEAR
Dataset automatically created during the evaluation run of model DreadPoor/Damasteel-8B-LINEAR
The dataset is composed of 38 configuration(s), each one corresponding 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 always pointing to the latest results.
An… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/DreadPoor__Damasteel-8B-LINEAR-details.DreadPoor__Autumn_Dawn-8B-LINEAR-details
Dataset Card for Evaluation run of DreadPoor/Autumn_Dawn-8B-LINEAR
Dataset automatically created during the evaluation run of model DreadPoor/Autumn_Dawn-8B-LINEAR
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/DreadPoor__Autumn_Dawn-8B-LINEAR-details.DreadPoor__Cadence-8B-LINEAR-details
Dataset Card for Evaluation run of DreadPoor/Cadence-8B-LINEAR
Dataset automatically created during the evaluation run of model DreadPoor/Cadence-8B-LINEAR
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/DreadPoor__Cadence-8B-LINEAR-details.DreadPoor__Decayed-8B-LINEAR-details
Dataset Card for Evaluation run of DreadPoor/Decayed-8B-LINEAR
Dataset automatically created during the evaluation run of model DreadPoor/Decayed-8B-LINEAR
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/DreadPoor__Decayed-8B-LINEAR-details.DreadPoor__CoolerCoder-8B-LINEAR-details
Dataset Card for Evaluation run of DreadPoor/CoolerCoder-8B-LINEAR
Dataset automatically created during the evaluation run of model DreadPoor/CoolerCoder-8B-LINEAR
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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/DreadPoor__CoolerCoder-8B-LINEAR-details.DreadPoor__Howdy-8B-LINEAR-details
Dataset Card for Evaluation run of DreadPoor/Howdy-8B-LINEAR
Dataset automatically created during the evaluation run of model DreadPoor/Howdy-8B-LINEAR
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/DreadPoor__Howdy-8B-LINEAR-details.DreadPoor__Oh_Boy-8B-LINEAR-details
Dataset Card for Evaluation run of DreadPoor/Oh_Boy-8B-LINEAR
Dataset automatically created during the evaluation run of model DreadPoor/Oh_Boy-8B-LINEAR
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/DreadPoor__Oh_Boy-8B-LINEAR-details.DreadPoor__Lydia_of_Whiterun-8B-LINEAR-details
Dataset Card for Evaluation run of DreadPoor/Lydia_of_Whiterun-8B-LINEAR
Dataset automatically created during the evaluation run of model DreadPoor/Lydia_of_Whiterun-8B-LINEAR
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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/DreadPoor__Lydia_of_Whiterun-8B-LINEAR-details.