davanstrien/kraken-olmbench-results-20260909
5.01 MB
Daniel van Strien PRO
davanstrien
AI & ML interests
Machine Learning Librarian
Recent Activity
updated a dataset about 3 hours ago
librarian-bots/model_cards_with_metadata updated a dataset about 3 hours ago
librarian-bots/dataset_cards_with_metadata updated a dataset about 5 hours ago
librarian-bots/dataset-columnsOrganizations
Posts 54
Post
3398
I fine-tuned a smol VLM to generate specialized art history metadata!
https://huggingface.co/davanstrien/iconclass-vlm: Qwen2.5-VL-3B trained using SFT to generate ICONCLASS codes (think Dewey Decimal for art!)
Trained with TRL + HF Jobs - single UV script, no GPU needed!
Space to explore predictions on a test set: davanstrien/iconclass-predictions
Blog soon!
https://huggingface.co/davanstrien/iconclass-vlm: Qwen2.5-VL-3B trained using SFT to generate ICONCLASS codes (think Dewey Decimal for art!)
Trained with TRL + HF Jobs - single UV script, no GPU needed!
Space to explore predictions on a test set: davanstrien/iconclass-predictions
Blog soon!
Articles 28
Article
25
FineBooks: are open OCR models good enough to unlock historical knowledge?
spaces 145
Running
28
Benchmark Leaderboard Race
🏁
Visualize AI model leaderboard rankings over time
Running
Agents
19
Historical Illustration Search
📚
Search and download British Library & Britannica images
Running
8
Dataset Lineage Explorer
🌿
Explore lineage of Hugging Face datasets and models
Running
WARC Explorer × HF Buckets
🗃
Browse WARCs streamed from public HF buckets
Sleeping
2
Temp Argilla
✍
Runtime error
5
Open Library Atlas
🗺
Explore high‑dimensional embeddings with an interactive map
models 296
davanstrien/finepdfs-edu-purpose-classifier
Text Classification • 0.1B • Updated • 23 • 1
davanstrien/Qwen2.5-0.5B-SFT
Text Generation • 0.5B • Updated • 84
davanstrien/internvl3_5-4b-iconclass-sft-brillfull
Updated • 16
davanstrien/internvl3_5-4b-iconclass-calib
Updated • 10
davanstrien/qwen3-vl-2b-iconclass-swift-test
Updated • 26
davanstrien/britannica-illustrated-detector
Image Classification • 7.52M • Updated • 87 • 1
davanstrien/britannica-illustration-detector-smoke
Object Detection • 10.2M • Updated • 137
davanstrien/autotrain-encyclopaedia-illustrations-blog-post-3327992158
Image Classification • Updated • 33
davanstrien/book-image-orientation
Updated
davanstrien/dataset-rows16-task-classifier-4096
Text Classification • 0.4B • Updated • 16
datasets 872
davanstrien/finepdfs-edu-purpose
Viewer • Updated • 230k • 25 • 1
davanstrien/bl-rotation-baseline
Viewer • Updated • 44 • 153
davanstrien/kraken-test-hf-stream
Viewer • Updated • 2 • 30
davanstrien/kraken-test-hf
Viewer • Updated • 2 • 30
davanstrien/kraken-test-arrow
Viewer • Updated • 2 • 45
davanstrien/britannica-clf-bhl-cross-eval
Viewer • Updated • 4.18k • 55
davanstrien/iconclass-eval-preds
Updated • 56
davanstrien/moh-ocr-sample-20
Viewer • Updated • 20 • 43
davanstrien/test-push-ia
Viewer • Updated • 88k • 88
davanstrien/bl-images-siglip2-index
Viewer • Updated • 1 • 99