What is "AI for libraries" beyond a catalogue chatbot? IMO: design patterns (OCR, extraction, classification, search), and agents that both run them and develop the small models behind them. As part of work with @natlibscot.bsky.social started a book on this: danielvanstrien.xyz/ai-patterns-...

Nouvelle leçon ! 💫 Une nouvelle traduction de la leçon de @danielvanstrien.bsky.social, Kaspar Beelen, @melvinwevers.bsky.social, @thomassmits.bsky.social, et @kmcdono.bsky.social. doi.org/10.46430/phfr0041

Can an open-weight coding agent match Claude Code at training a domain-specific model? Same prompt. ~13 min each. Pushed to Hugging Face. Pi + Kimi K2.6 vs Claude Code + Opus 4.7. Task: classify NC session laws (1866-1967) as Jim Crow or not. Full write-up: danielvanstrien.xyz/posts/2026/a...

Can an open-weight coding agent match Claude Code at training a domain-specific model? Same prompt. ~13 min each. Pushed to Hugging Face. Pi + Kimi K2.6 vs Claude Code + Opus 4.7. Task: classify NC session laws (1866-1967) as Jim Crow or not. Full write-up: danielvanstrien.xyz/posts/2026/a...

2 million book titles visualised as an interactive Embedding Atlas. Fiction, History, Science — each forms its own cluster. The trick: mount the same @hf.co Bucket to a GPU Job AND a Space. Job writes, Space reads. No uploads!

Segment any object in an image dataset with a text prompt — one command. uv run segment-objects.py data output --class-name deer Pixel-level masks via SAM3. Perfect for agents building their own training data. Runs on @hf.co Jobs. huggingface.co/datasets/uv-...

Wanted to share a personal project I've been working on: I love classic literature, and I'm also taking an AI class here at UIUC, so I trained an LLM from scratch on Victorian lit from 1837 to 1899. This is Mr. Chatterbox, the Victorian Gentleman Chatbot: huggingface.co/spaces/tvent...

You never know what data will be used for! I uploaded a @britishlibrary.bsky.social dataset to Hugging Face in 2022. IIRC one of my first PR to a HF repo! 4 years later, someone trains a Victorian chatbot on it More libraries should be sharing their public domain collections for AI to build on!

Is olmOCR-bench getting close to saturation? Top score is now 85.9%. Yesterday, Datalab took #1 with chandra-ocr-2. A year ago, the best was 79. Visualised the race to get there using @hf.co leaderboard data

One of the nicest things about Nvidia model releases is that they ship the training data. What does it look like? I sampled 250k examples from 24 datasets in the Nemotron post-training v3 collection and built an interactive Embedding Atlas to explore it.

The new @hf.co storage Buckets open up the Hub beyond models and datasets. Example: IIIF image hosting. With Buckets, just upload static tiles and any IIIF viewer zooms straight from CDN!

The new @hf.co storage Buckets open up the Hub beyond models and datasets. Example: IIIF image hosting. With Buckets, just upload static tiles and any IIIF viewer zooms straight from CDN!

74GB of Dutch PDFs, filtered and written back to the Hub - without touching local disk! Hub is your disk! I built a PoC adding sink_parquet for @pola.rs to stream writes to @hf.co's new Storage Buckets via Xet. Constant memory ~18 min on a 2-vCPU machine.

There is no best VLM OCR model - rankings can flip completely by document type. I built ocr-bench: run open OCR models on YOUR documents, get a per-collection leaderboard. VLM-as-judge with Bradley-Terry ELO, all running on @hf.co. No local GPU needed.

Is it worth re-OCR'ing old library index cards? Re-OCR'd 453,000 from @bpl.boston.gov's rare books catalogue. ~$50 compute using @huggingface Jobs BPL's own guide calls their search "extremely unreliable." Does better OCR + semantic search help fix it? Demo space link below

Is it worth re-OCR'ing old library index cards? Re-OCR'd 453,000 from @bpl.boston.gov's rare books catalogue. ~$50 compute using @huggingface Jobs BPL's own guide calls their search "extremely unreliable." Does better OCR + semantic search help fix it? Demo space link below

Ran the same OCR models on 68 pages of historic newspaper. Every model hallucinated or looped. DeepSeek-OCR-2, LightOnOCR-2, GLM-OCR – all melt down on dense newspaper columns. You can try yourself using this @hf.co dataset: huggingface.co/datasets/dav...

Ran the same OCR models on 68 pages of historic newspaper. Every model hallucinated or looped. DeepSeek-OCR-2, LightOnOCR-2, GLM-OCR – all melt down on dense newspaper columns. You can try yourself using this @hf.co dataset: huggingface.co/datasets/dav...

Llama.cpp joins Hugging Face github.com/ggml-org/lla...

Wrote a slightly more detailed guide on how to do this with your own collections/materials: danielvanstrien.xyz/posts/2026/r...

Llama.cpp joins Hugging Face github.com/ggml-org/lla...

Re-OCR'd the complete 1771 Encyclopaedia Britannica (2,724 pages) with a single command on @hf.co Jobs. - 0.9B model (GLM-OCR) ~$0.002/page ~$5 total on an L4 GPU Before (old Tesseract ocr) → After

The uv-scripts/ocr collection now includes 13 models, including GLM-OCR, a 0.9B model that scores 94.6% on OmniDocBench. One command to run any of them on your dataset via @hf.co Jobs. huggingface.co/datasets/uv-...

Join us tomorrow for a demo of IIIF Illustration Detector! Zoom link: iiif.io/community

Datasets and benchmarks drive AI progress, but finding papers that introduce new ones means digging through thousands of arXiv abstracts. Updated the Dataset Papers on ArXiv app to surface them: 52K+ papers classified as introducing new datasets from 212K CS papers.

Join us Feburary 11 for a demo of @danielvanstrien.bsky.social's IIIF Illustration Detector. Zoom on the IIIF Community Calendar: iiif.io/community

Built an object detector from zero-labelled data in one afternoon with help from Claude Code (it can do more than vibe code, TODO apps...) SAM3 on HF Jobs → correct the errors → train YOLO → repeat. Three rounds: 31% → 99% accuracy on historical index cards from @natlibscot.bsky.social

Built an object detector from zero-labelled data in one afternoon with help from Claude Code (it can do more than vibe code, TODO apps...) SAM3 on HF Jobs → correct the errors → train YOLO → repeat. Three rounds: 31% → 99% accuracy on historical index cards from @natlibscot.bsky.social

We used to do real science

Built a 2.5MB image classifier that runs in the browser in an evening with Claude Code. I used a dataset I labelled in 2022 and left on @hf.co for 3 years 😬. It finds illustrated pages in historical books. No server. No GPU.

Built a 2.5MB image classifier that runs in the browser in an evening with Claude Code. I used a dataset I labelled in 2022 and left on @hf.co for 3 years 😬. It finds illustrated pages in historical books. No server. No GPU.

Just posted my slides from the AI4LAM #FF2025 workshop on open source AI for GLAMs. Probably slides on their own aren't that useful, but they do feature one of my growing collection of libraries-and-AI memes, so there's that danielvanstrien.xyz/slides.html

At the AI4LAM Fantastic Futures conference this week Happy to chat about @hf.co, open source AI for GLAMs, or why cultural heritage should bet on small, focused models over closed-source giants! DM or find me at breaks! #AI4LAM #FF2025

Building datasets to train smaller, task-focused models used to be incredibly time-consuming. Very excited to see SAM3 massively lower that barrier. Describe the class you want to detect and get annotated datasets automatically! Try it yourself: huggingface.co/datasets/uv-...!

Very much looking forward to presenting at this tomorrow. I will be making my usual pitch that datasets are the foundational infrastructure for cultural heritage to benefit from and create useful AI models and tools. Be warned, I did fire up the meme generator for my slides...

Over the last 24 hours, I have finetuned three Qwen3-VL models (2B, 4B, and 8B) on the CATmuS dataset on @hf.co . The first version of the models are now available on the Small Models for GLAM organization with @danielvanstrien.bsky.social (Links below) Working on improving them further.

DeepSeek-OCR just got vLLM support 🚀 Currently processing @natlibscot.bsky.social's 27,915-page handbook collection with one command. Processing at ~350 images/sec on A100 Using @hf.co Jobs + uv - zero setup batch OCR! Will share final time + cost when done!

🤗 Sentence Transformers is joining @hf.co! 🤗 This formalizes the existing maintenance structure, as I've personally led the project for the past two years on behalf of Hugging Face. I'm super excited about the transfer! Details in 🧵

OCR is one of AI's oldest challenges (first systems: early 1900s!) Modern vision-language models have transformed what's possible: handwriting, 100+ languages, math formulas, tables, signature extraction... New @hf.co guide on OCR huggingface.co/blog/ocr-ope...

Small models work great for GLAM but there aren't enough examples! With @wjbmattingly.bsky.social I'm launching small-models-for-glam on @hf.co to create/curate models that run on modest hardware and address GLAM use cases. Follow the org to keep up-to-date! huggingface.co/small-models...

Very nice work! IMO, this is the kind of topic that more libraries/GLAM/DH people should be working on. The training of these models is *relatively* simple. As always, the missing ingredient is readily accessible data.

It's been brewing for months: @inriaparisnlp.bsky.social releases CoMMA (Corpus of Multilingual Medieval Archives) ! 📚 2.5bn tokens of mostly Latin and French texts 🕰️ 800→1600 CE 📜 23k manuscripts 🖥️ 18k on the reading interface: comma.inria.fr 🔍 Paper: inria.hal.science/hal-05299220v1 (1/🧵)

Another week, another VLM-based OCR model! Nanonets just released OCR2 - a 3B parameter vision-language model for document OCR 📄 You can run it with one command on @hf.co Jobs (no local GPU needed)

Another week, another VLM-based OCR model! Nanonets just released OCR2 - a 3B parameter vision-language model for document OCR 📄 You can run it with one command on @hf.co Jobs (no local GPU needed)

DoTS.ocr just got native vLLM support! I built a UV script so you can run SOTA multilingual OCR in seconds with zero setup using @hf.co Jobs Tested on 1800s library cards - works great ✨

DoTS.ocr just got native vLLM support! I built a UV script so you can run SOTA multilingual OCR in seconds with zero setup using @hf.co Jobs Tested on 1800s library cards - works great ✨

Card catalogues aren't just a relic of the past - many institutions still rely on them because full migration is too expensive. VLMs could help change that. I uploaded two new @hf.co datasets (~470K cards) for training/evaluating models to extract structured metadata from catalogue cards.

We’re hiring for two machine learning roles. A chance to do cutting edge things with ML to make this place a lot more personalized. jobs.gem.com/bluesky/am9i...