🤖AI❤️Data enjoyer , building robots to helps folks learn things quicker.

Paris, France
Joined April 2009
👨🏻‍🎨I'm a space artiste
2
1
14
13,685
Lyra with a broadcast sized audience 🤯👇🏻
if you have a qwen3.5 4b around, please try steering neurons L14 N8949 +1 and L13 N7956 -1 now you have evil qwen recipe: dose × median(‖resid‖ leaving layer L, tokens 1:) / ‖W_down[:, n]‖` at the down_proj at every input
3
131
Joseph Pollack #Ï 🎗️ retweeted
Yesterday, a russian Geran-4/5 struck the Hospital and Institute of Cardiology in Solom'yanka, Kyiv 50.420375, 30.459610 @GeoConfirmed t.me/gunpKyiv/17593 t.me/kievinfo_kyiv/104064
3
37
5
132
20,440
Meanwhile criminals in the @KremlinRussia continue to deliberately target health infrastructure in a genocidal bid to cause mass population movements and death to steal their belongings . Public health is #notatarget Help stop the war by donating to: u24.gov.ua
Another ballistic missile in the 3am wave impacted right outside Shuliavska Polyclinic, next to the mall struck in the QT. 50.451698, 30.445697 @GeoConfirmed Reference: maps.app.goo.gl/gbr1kGyQ1uni… t.me/kyivtv/155328
1
60
Joseph Pollack #Ï 🎗️ retweeted
We release SlideOn and mSlideOn at @LightOnIO today, two sota sparse retrievers, models designed by @paulomouraj and I. Those models are really strong for first stage retrieval, you can add then a multi-vector model as a reranker and then a decision model 👇
We surfed the dense and late-interaction waves… now it's time to SlideOn sparse retrieval 🐕 🚀 Meet SlideOn and mSlideOn, fully open SOTA sparse retrievers at 174M and 339M parameters, trained by @LightOnIO R&D Models: huggingface.co/collections/l… Blog: huggingface.co/blog/lightona…
4
9
45
1,467
Joseph Pollack #Ï 🎗️ retweeted
Ukraine’s 21st KRAKEN Unmanned Systems Regiment says its MURAMASA operators scored their first hit on a Russian TOS-3 Drakon heavy flamethrower system during Operation Vivaldi. The TOS-3 is one of Russia’s newest weapons systems. #Ukraine
3
41
2
286
19,535
Ben decels until he pushes hf datasets😔🤷🏻‍♂️
2
91
Meanwhile every European country has recorded dozens of terrorist attacks sponsored by the @KremlinRussia . You can help save lives by writing to your representative demanding a response or donate to u24.gov.ua
Replying to @NOELreports
we went from a few recon drones a year ago not being considered escalation, to 2 dozen civilians murdered and 2 ships sunk by russia not considered an escalation
84
Wake up hun new programming language just dropped - follow @Chi_Wang_ 😉👇🏻check out vxlang.com
69
I’ll take that bet : mandarin is the superior concept-per-token language . 🤝
This quoted post is unavailable.
1
414
Joseph Pollack #Ï 🎗️ retweeted
Direct strike on a hospital. Savages.
This morning, a russian Shahed struck a hospital in Zaporizhzhia 47.844764, 35.140323 @GeoConfirmed t.me/dsns_telegram/75650 t.me/riamelitopolua/94865 🤝 @99Dominik_
6
262
6
1,127
26,670
Joseph Pollack #Ï 🎗️ retweeted
Russian drones are hitting book warehouses all across Ukraine, becuase the destruction of Ukrainian language and culture is one their war's central goals. nytimes.com/2026/09/25/world…
139
1,758
77
3,129
112,750
the Readmes are really well done , and a lot of depth is shared here , which is nice. github.com/featherless-ai/si…
We are jev-ifying open source models @FeatherlessAI - which surpasses jev in evals - and includes image/vision With a starting price of [check notes]... Free? simple-jev-demo-api.featherl…
1
286
This is great for lerobot datasets
New JS package: @huggingface/lerobot 🤖 Read LeRobot datasets on the Hub straight from the browser. No download. Point your coding agent at it and build custom viewers fast. Example 3D camera-frustum replay streams 1.1 MB of a 793 MB dataset: hf.co/spaces/mishig/lerobot-…
163
Xiaomi did a really nice job with CodeMidas paper sharing knowledge and experience in massively distributed RL using agents. The one thing I do like in this timeline is seeing decades of promoting Chinese open source collaboration finally coming to bear and it’s better than exp
109
The backwards American citizen will be very glad to receive low value dirt from a bloodthirsty dictatorship . They might even do a traditional dance when the container ships roll on in like they did for the urea shipments in South Africa
74
This is actually cool for folks that expand base and instruct models with new/better tokenizers
Tokenizers v1's first release candidate is out 🔥 absolutely huge release across the board: Up to 30x faster tokenization, rivaling the best in the ecosystem. Scaling across threads, much better latency, less memory consumed, and microscopic crate size. huggingface.co/blog/tokenize…
2
220
Meanwhile , criminals in the @KremlinRussia gleefully continue to target public health facilities in their genocidal bid to murder civilians and thieve as much as they can . stop this by writing by to your rep to demand air defense or by donating here u24.gov.ua
It is reported that Russia attacked a warehouse belonging to one of the largest pharmaceutical distributors in Odesa.
90
AI’s accessibility implications are actually really valuable for society
If you're blind, most PDFs are a garbled mess - and having one fixed can cost >$100. Our API now makes them usable for pennies.
158
Pro tip : it’s always the data 😉😅✌🏻 🔥New hugginchat by @huggingface is lit
so many possibilities what should I start with
85
Huggingfacers might even learn log scales @NVIDIAAI … it’s gonna get weird ( in a good way! )
A 15.9M-parameter specialist OCR model outperforms many VLMs hundreds of times larger. On a 2,165-page historical eval dataset, Kraken PP-OCRv6 ranks #4 on reading CER and #1 when long-s, ligatures and case are preserved. Fun fact: I had to adjust the plotting logic to get it to show properly because the model does so well! huggingface.co/spaces/finebo…
2
451