datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
Qwen3-0.6B-pts-steering-vectors
PTS Steering Vectors Dataset
A dataset of activation-based steering vectors created using the Pivotal Token Search (PTS) technique.
Details
Source: Generated using the PTS tool
Model: Qwen/Qwen3-0.6B
Dataset Structure
This dataset contains:
steering_vectors.jsonl: The main file with token-level steering vectors
Usage
These steering vectors can be used for activation-based steering during inference to guide language models toward particular… See the full description on the dataset page: https://huggingface.co/datasets/codelion/Qwen3-0.6B-pts-steering-vectors.open-web-vectors-manifest
Open Web Vector Initiative — Site Manifest
Per-site metadata for every site in the Open Web Vector Initiative, including
what each site told us about AI use on the day we asked.
The initiative — how the permission gate works, and what we will and will
not publish: https://divinci.ai/open-web-vectors/
The live directory — search the corpus, chat with any site in it, or claim
your own: https://divinci.ai/www-rag/
This dataset contains no page text and no embeddings. That is… See the full description on the dataset page: https://huggingface.co/datasets/Divinci-AI/open-web-vectors-manifest.llm-eval-requestsDelta-Vector__Henbane-7b-attempt2-details
Dataset Card for Evaluation run of Delta-Vector/Henbane-7b-attempt2
Dataset automatically created during the evaluation run of model Delta-Vector/Henbane-7b-attempt2
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/Delta-Vector__Henbane-7b-attempt2-details.Delta-Vector__Baldur-8B-details
Dataset Card for Evaluation run of Delta-Vector/Baldur-8B
Dataset automatically created during the evaluation run of model Delta-Vector/Baldur-8B
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 additional… See the full description on the dataset page: https://huggingface.co/datasets/open-llm-leaderboard/Delta-Vector__Baldur-8B-details.unbias-plus-dataset
Unbias Dataset
This dataset contains configurations used for the Unbias project at the Vector Institute:
train_4 (config, default): Our newest and highest quality training split.
other_splits (config): Contains the earlier splits below.
train_1: Training split sourced from VLDBench (regenerated version).
train_2: Another training split.
train_3: Another training split.
test_set: Test split sourced from BABE Golden 500.
⭐ train_4 is our newest, highest quality… See the full description on the dataset page: https://huggingface.co/datasets/vector-institute/unbias-plus-dataset.qsd-eval-vectorsvector-9-17-sft1vector-sft2Factuality_Alignment
Factual Preference Alignment Dataset
**⚠️ Warning:**This dataset contains hallucinated and synthetic responses
intentionally generated for research on robust factuality alignment.
Responses may include fabricated or incorrect information by design
to support the evaluation of hallucination-aware learning.
Dataset Summary
The AIXpert Preference Alignment Dataset is a curated collection of
45,000 factuality-aware preference pairs designed to support
research on Modified… See the full description on the dataset page: https://huggingface.co/datasets/vector-institute/Factuality_Alignment.vector-sft3vector-9-14-sft2vector-9-14mmnga__Llama-3-70B-japanese-suzume-vector-v0.1-details
Dataset Card for Evaluation run of mmnga/Llama-3-70B-japanese-suzume-vector-v0.1
Dataset automatically created during the evaluation run of model mmnga/Llama-3-70B-japanese-suzume-vector-v0.1
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/mmnga__Llama-3-70B-japanese-suzume-vector-v0.1-details.Delta-Vector__Darkens-8B-details
Dataset Card for Evaluation run of Delta-Vector/Darkens-8B
Dataset automatically created during the evaluation run of model Delta-Vector/Darkens-8B
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/Delta-Vector__Darkens-8B-details.Delta-Vector__Control-8B-V1.1-details
Dataset Card for Evaluation run of Delta-Vector/Control-8B-V1.1
Dataset automatically created during the evaluation run of model Delta-Vector/Control-8B-V1.1
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/Delta-Vector__Control-8B-V1.1-details.Delta-Vector__Control-8B-details
Dataset Card for Evaluation run of Delta-Vector/Control-8B
Dataset automatically created during the evaluation run of model Delta-Vector/Control-8B
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/Delta-Vector__Control-8B-details.Delta-Vector__Tor-8B-details
Dataset Card for Evaluation run of Delta-Vector/Tor-8B
Dataset automatically created during the evaluation run of model Delta-Vector/Tor-8B
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/Delta-Vector__Tor-8B-details.Ursa-Refined-Mini-pileseal-7b-apps-vectorDelta-Vector__Odin-9B-details
Dataset Card for Evaluation run of Delta-Vector/Odin-9B
Dataset automatically created during the evaluation run of model Delta-Vector/Odin-9B
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/Delta-Vector__Odin-9B-details.USACO
USACO Dataset
This dataset contains problems from the USA Computing Olympiad (USACO) organized by seasons. Each season runs from November of the previous year → October of the current year, plus the US Open. One JSONL file per season is provided (usaco_<season>.jsonl) for efficient storage and loading.
Dataset Statistics
Total Problems: 680
Total Seasons: 14
Total Sample Cases: 854
Total Test Cases: 9,055
Data Structure
Each record contains:
id: Unique… See the full description on the dataset page: https://huggingface.co/datasets/vectorzhou/USACO.LOJ
LOJ Dataset
This dataset contains problems from the LibreOJ (LOJ) platform. All problems are stored in a single JSONL file for efficient storage and loading.
Dataset Statistics
Total Problems: 320
Total Sample Cases: 371
Total Test Cases: 4,150
Problems with Custom Checkers: 14
Data Structure
Each record contains:
id: Unique stable identifier for the problem
problem_id: Original LOJ problem ID
problem_statement: List of problem statements in different styles… See the full description on the dataset page: https://huggingface.co/datasets/vectorzhou/LOJ.trait-vectorsUrsa-ShortStories-Allura-Filtered