datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
wan2.2-LorasLTX2.3-22B_IC-LoRA-CrossView-Prompt-Dataset
CrossView Prompt Dataset
The training dataset behind the
CrossView Prompt IC-LoRA
for LTX-Video 2.3 — a "virtual second camera" adapter that re-renders a scene
from a new viewpoint described by a short prompt.
Each sample is a pair of static-camera clips of the same scene (a reference
view and a target view) plus a camera-delta caption describing how the
target camera differs from the reference.
Contents
clips/<scene>/<cam>.mp4 # 504 unique clips, native… See the full description on the dataset page: https://huggingface.co/datasets/Cseti/LTX2.3-22B_IC-LoRA-CrossView-Prompt-Dataset.LoRA-Merge-Imageshex-lora-opus-magnum-instructions-only-results
hex-lora-opus-magnum-instructions-only-results
Held-out evaluation logs for the same 6-LoRA RL sweep as
opus-magnum-rl-eval, but on a much harder eval task:
the 57-puzzle "instructions-only" set drawn from the
Opus Magnum campaign + curated
holdout puzzles. The agent runs an interactive Python REPL and must submit()
a working .solution file to the in-game verifier.
`57 puzzles × 6 epochs × (9 LoRA-sweep variants + 2 27B mt=4096 reruns
2 Gemini Flash baselines) = 4446 trajectories`.… See the full description on the dataset page: https://huggingface.co/datasets/robhaisfield/hex-lora-opus-magnum-instructions-only-results.mlabonne__Hermes-3-Llama-3.1-70B-lorablated-details
Dataset Card for Evaluation run of mlabonne/Hermes-3-Llama-3.1-70B-lorablated
Dataset automatically created during the evaluation run of model mlabonne/Hermes-3-Llama-3.1-70B-lorablated
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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/mlabonne__Hermes-3-Llama-3.1-70B-lorablated-details.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.LEESM__llama-2-7b-hf-lora-oki100p-details
Dataset Card for Evaluation run of LEESM/llama-2-7b-hf-lora-oki100p
Dataset automatically created during the evaluation run of model LEESM/llama-2-7b-hf-lora-oki100p
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/LEESM__llama-2-7b-hf-lora-oki100p-details.repro-understanding-lora-as-knowledge-memory-an-empirical-analysis-traces
Agent traces
Agent sessions published from a Trackio Logbook.
skyyrose-lora-dataset-v1utkmst__chimera-beta-test2-lora-merged-details
Dataset Card for Evaluation run of utkmst/chimera-beta-test2-lora-merged
Dataset automatically created during the evaluation run of model utkmst/chimera-beta-test2-lora-merged
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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/utkmst__chimera-beta-test2-lora-merged-details.siglip2-large-lora-v1-dataset
SigLIP2-Large LoRA v1 — Training Pairs
Material/surface visual-similarity training pairs for fine-tuning
SigLIP2-large with LoRA + Supervised Contrastive loss. Each row links a
catalog product image to one polygon-clipped material crop from a SAM3-segmented
interior room render.
Statistics
Split
Rows
train
5,618
eval
576
Layout
.
├── dataset.jsonl train split (one JSON object per line)
├── eval.jsonl held-out eval split
└──… See the full description on the dataset page: https://huggingface.co/datasets/subhrokomol/siglip2-large-lora-v1-dataset.JMT-Bench-result_self-rewarding_Mistral-7B-lora
JMT-Bench result
Answer language
JMT-Benchの回答のうち、Englishで回答した件数
Model
Count
mistralai/Mistral-7B-v0.3
25
HachiML/Mistral-7B-v0.3-m1-lora
7
HachiML/Mistral-7B-v0.3-m2-lora
7
HachiML/Mistral-7B-v0.3-m3-lora
2
nbeerbower__Llama-3.1-Nemotron-lorablated-70B-details
Dataset Card for Evaluation run of nbeerbower/Llama-3.1-Nemotron-lorablated-70B
Dataset automatically created during the evaluation run of model nbeerbower/Llama-3.1-Nemotron-lorablated-70B
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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/nbeerbower__Llama-3.1-Nemotron-lorablated-70B-details.ehristoforu__fd-lora-merged-16x32-details
Dataset Card for Evaluation run of ehristoforu/fd-lora-merged-16x32
Dataset automatically created during the evaluation run of model ehristoforu/fd-lora-merged-16x32
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/ehristoforu__fd-lora-merged-16x32-details.DreadPoor__Aurora_faustus-8B-LORABLATED-details
Dataset Card for Evaluation run of DreadPoor/Aurora_faustus-8B-LORABLATED
Dataset automatically created during the evaluation run of model DreadPoor/Aurora_faustus-8B-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 pointing to the… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/DreadPoor__Aurora_faustus-8B-LORABLATED-details.ehristoforu__fd-lora-merged-64x128-details
Dataset Card for Evaluation run of ehristoforu/fd-lora-merged-64x128
Dataset automatically created during the evaluation run of model ehristoforu/fd-lora-merged-64x128
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/ehristoforu__fd-lora-merged-64x128-details.DreadPoor__Aurora_faustus-8B-LORABLATED_ALT-details
Dataset Card for Evaluation run of DreadPoor/Aurora_faustus-8B-LORABLATED_ALT
Dataset automatically created during the evaluation run of model DreadPoor/Aurora_faustus-8B-LORABLATED_ALT
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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/DreadPoor__Aurora_faustus-8B-LORABLATED_ALT-details.ehristoforu__qwen2.5-with-lora-think-3b-it-details
Dataset Card for Evaluation run of ehristoforu/qwen2.5-with-lora-think-3b-it
Dataset automatically created during the evaluation run of model ehristoforu/qwen2.5-with-lora-think-3b-it
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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/ehristoforu__qwen2.5-with-lora-think-3b-it-details.thinkcoder__llama3-8b-instruct-lora-8-sft-details
Dataset Card for Evaluation run of thinkcoder/llama3-8b-instruct-lora-8-sft
Dataset automatically created during the evaluation run of model thinkcoder/llama3-8b-instruct-lora-8-sft
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/thinkcoder__llama3-8b-instruct-lora-8-sft-details.spd80-9b-loranbeerbower__Mahou-1.5-mistral-nemo-12B-lorablated-details
Dataset Card for Evaluation run of nbeerbower/Mahou-1.5-mistral-nemo-12B-lorablated
Dataset automatically created during the evaluation run of model nbeerbower/Mahou-1.5-mistral-nemo-12B-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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/nbeerbower__Mahou-1.5-mistral-nemo-12B-lorablated-details.bunnycore__SmolLM2-1.7B-roleplay-lora-details
Dataset Card for Evaluation run of bunnycore/SmolLM2-1.7B-roleplay-lora
Dataset automatically created during the evaluation run of model bunnycore/SmolLM2-1.7B-roleplay-lora
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/bunnycore__SmolLM2-1.7B-roleplay-lora-details.SkyOrbis__SKY-Ko-Llama3.2-3B-lora-epoch1-details
Dataset Card for Evaluation run of SkyOrbis/SKY-Ko-Llama3.2-3B-lora-epoch1
Dataset automatically created during the evaluation run of model SkyOrbis/SKY-Ko-Llama3.2-3B-lora-epoch1
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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/SkyOrbis__SKY-Ko-Llama3.2-3B-lora-epoch1-details.SkyOrbis__SKY-Ko-Llama3.2-1B-lora-v2-epoch5-details
Dataset Card for Evaluation run of SkyOrbis/SKY-Ko-Llama3.2-1B-lora-v2-epoch5
Dataset automatically created during the evaluation run of model SkyOrbis/SKY-Ko-Llama3.2-1B-lora-v2-epoch5
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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/SkyOrbis__SKY-Ko-Llama3.2-1B-lora-v2-epoch5-details.SkyOrbis__SKY-Ko-Llama3.1-8B-lora-details
Dataset Card for Evaluation run of SkyOrbis/SKY-Ko-Llama3.1-8B-lora
Dataset automatically created during the evaluation run of model SkyOrbis/SKY-Ko-Llama3.1-8B-lora
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/SkyOrbis__SKY-Ko-Llama3.1-8B-lora-details.SkyOrbis__SKY-Ko-Llama3.1-8B-lora-epoch1-details
Dataset Card for Evaluation run of SkyOrbis/SKY-Ko-Llama3.1-8B-lora-epoch1
Dataset automatically created during the evaluation run of model SkyOrbis/SKY-Ko-Llama3.1-8B-lora-epoch1
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/SkyOrbis__SKY-Ko-Llama3.1-8B-lora-epoch1-details.lora-rules-dataset
LoRA Rules Dataset
Synthetic behavioral rules dataset for training a hypernetwork that generates
LoRA adapters on-the-fly from structured rule strings.
Format
Each record is a JSON line with fields:
rule_id — unique identifier
rule_type — one of: Constraint, Format, Knowledge, Persona, Safety, Tone
weight — float 0.0–1.0, importance of the rule
description — natural language rule description
raw — full rule string [RuleType|Weight] Description
training_examples — list of… See the full description on the dataset page: https://huggingface.co/datasets/broadfield-dev/lora-rules-dataset.lora-rules-qwen3-0.6b-r8-n180
LoRA Rules Dataset
Synthetic behavioral rules dataset for training a hypernetwork that generates
LoRA adapters on-the-fly from structured rule strings.
Format
Each record is a JSON line with fields:
rule_id — unique identifier
rule_type — one of: Constraint, Format, Knowledge, Persona, Safety, Tone
weight — float 0.0–1.0, importance of the rule
description — natural language rule description
raw — full rule string [RuleType|Weight] Description
training_examples — list of… See the full description on the dataset page: https://huggingface.co/datasets/broadfield-dev/lora-rules-qwen3-0.6b-r8-n180.monsterapi__gemma-2-2b-LoRA-MonsterInstruct-details
Dataset Card for Evaluation run of monsterapi/gemma-2-2b-LoRA-MonsterInstruct
Dataset automatically created during the evaluation run of model monsterapi/gemma-2-2b-LoRA-MonsterInstruct
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… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/monsterapi__gemma-2-2b-LoRA-MonsterInstruct-details.SkyOrbis__SKY-Ko-Llama3.2-3B-lora-epoch3-details
Dataset Card for Evaluation run of SkyOrbis/SKY-Ko-Llama3.2-3B-lora-epoch3
Dataset automatically created during the evaluation run of model SkyOrbis/SKY-Ko-Llama3.2-3B-lora-epoch3
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/SkyOrbis__SKY-Ko-Llama3.2-3B-lora-epoch3-details.