sprint
Datasets
All datasets matching “sprint”sprintduplicatequestions-pairclassification
SprintDuplicateQuestions
An MTEB dataset
Massive Text Embedding Benchmark
Duplicate questions from the Sprint community.
Task category
t2t
Domains
Programming, Written
Reference
https://www.aclweb.org/anthology/D18-1131/
How to evaluate on this task
You can evaluate an embedding model on this dataset using the following code:
import mteb
task = mteb.get_tasks(["SprintDuplicateQuestions"])
evaluator = mteb.MTEB(task)
model = mteb.get_model(YOUR_MODEL)… See the full description on the dataset page: https://huggingface.co/datasets/mteb/sprintduplicatequestions-pairclassification.biodex_sprint1
BioDex Aviary Birds — Sprint 1
Image-classification dataset for the 55 bird species held in the Parque aviary
(2026 catalogue). Built for training a species classifier that runs on photos
visitors and keepers take on-site.
75,082 images · 55 classes · 224×224 RGB JPEG · train / val / test splits ·
GPU data-augmentation on the training split.
Each column is one source image — top: original, below: its two augmented copies (rotation, lighting, motion blur, flip).
How… See the full description on the dataset page: https://huggingface.co/datasets/santianwandter/biodex_sprint1.temp-xc-btk-sprint-artifacts
temp-xc btk-sprint artifacts
Artifacts from the 2026-07-26/27 "batch_topk" sprint (branch
dmitry-btk-txc-sprint of chainik1125/temp_xc): the paper-arch
activation 2×2 (per-window vs batch-pooled selection × ReLU placement)
and the §5.3 EM window-scaling sweep.
Contents
em_checkpoints/<train_key>/ — trained EM dictionaries
(model.safetensors + config.json), Qwen2.5-7B-Instruct L15
medical-organism task, d_sae=32768, canonical 25k-step training.
Arms: txc_base… See the full description on the dataset page: https://huggingface.co/datasets/dmanningcoe/temp-xc-btk-sprint-artifacts.etrack-sprint-smoketml26_task1sprintduplicatequestions-pairclassification-vn
How to evaluate on this task
You can evaluate an embedding model on this dataset using the following code:
import mteb
task = mteb.get_tasks(["SprintDuplicateQuestions-VN"])
evaluator = mteb.MTEB(task)
model = mteb.get_model(YOUR_MODEL)
evaluator.run(model)
To learn more about how to run models on mteb task check out the GitHub repitory.
Citation
If you use this dataset, please cite the dataset as well as mteb, as this dataset likely includes additional… See the full description on the dataset page: https://huggingface.co/datasets/GreenNode/sprintduplicatequestions-pairclassification-vn.