Daniël de Kok
@danieldk.eu
Machine Learning, Natural Language Processing, LLM, transformers, macOS, NixOS, Rust, C++, Python, Cycling.
Working on inference at Hugging Face 🤗. Open source ML 🚀.
Working on inference at Hugging Face 🤗. Open source ML 🚀.
Pinned
Daniël de Kok
@danieldk.eu
· Nov 18
I create a starter pack of current and former @explosion-ai.bsky.social. Give some of the people who made spaCy, Prodigy, Thinc, etc. a follow:
go.bsky.app/VngRFva
go.bsky.app/VngRFva
Reposted by Daniël de Kok
Training LLMs end to end is hard. But way more people should, and will, be doing it in the future.
The @hf.co Research team is excited to share their new e-book that covers the full pipeline:
· pre-training,
· post-training,
· infra.
200+ pages of what worked and what didn’t. ⤵️
The @hf.co Research team is excited to share their new e-book that covers the full pipeline:
· pre-training,
· post-training,
· infra.
200+ pages of what worked and what didn’t. ⤵️
November 2, 2025 at 3:17 PM
Training LLMs end to end is hard. But way more people should, and will, be doing it in the future.
The @hf.co Research team is excited to share their new e-book that covers the full pipeline:
· pre-training,
· post-training,
· infra.
200+ pages of what worked and what didn’t. ⤵️
The @hf.co Research team is excited to share their new e-book that covers the full pipeline:
· pre-training,
· post-training,
· infra.
200+ pages of what worked and what didn’t. ⤵️
Reposted by Daniël de Kok
The Hub is on 100% on Xet. 🚀
A little over a year ago, @hf.co acquired XetHub to unlock the next phase of growth in models and datasets. huggingface.co/blog/xethub-...
In April, there were 1,000 Hugging Face repos on Xet. Now every repo (over 6M) on the Hub is on Xet.
A little over a year ago, @hf.co acquired XetHub to unlock the next phase of growth in models and datasets. huggingface.co/blog/xethub-...
In April, there were 1,000 Hugging Face repos on Xet. Now every repo (over 6M) on the Hub is on Xet.
October 3, 2025 at 3:16 PM
The Hub is on 100% on Xet. 🚀
A little over a year ago, @hf.co acquired XetHub to unlock the next phase of growth in models and datasets. huggingface.co/blog/xethub-...
In April, there were 1,000 Hugging Face repos on Xet. Now every repo (over 6M) on the Hub is on Xet.
A little over a year ago, @hf.co acquired XetHub to unlock the next phase of growth in models and datasets. huggingface.co/blog/xethub-...
In April, there were 1,000 Hugging Face repos on Xet. Now every repo (over 6M) on the Hub is on Xet.
We made a blog post on how you can use kernel-builder to develop and build compute kernels for the @hf.co Kernel Hub:
huggingface.co/blog/kernel-...
huggingface.co/blog/kernel-...
From Zero to GPU: A Guide to Building and Scaling Production-Ready CUDA Kernels
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
August 19, 2025 at 11:06 AM
We made a blog post on how you can use kernel-builder to develop and build compute kernels for the @hf.co Kernel Hub:
huggingface.co/blog/kernel-...
huggingface.co/blog/kernel-...
Yesterday we released support for GPT OSS (the new OpenAI open weight model) across the @hf.co ecosystem. The latest Transformers now integrates support for the kernels package and uses kernels from the HF Kernel Hub to run models like GPT OSS as fast as possible. 🚀
huggingface.co/blog/welcome...
huggingface.co/blog/welcome...
Welcome GPT OSS, the new open-source model family from OpenAI!
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
August 6, 2025 at 8:42 PM
Yesterday we released support for GPT OSS (the new OpenAI open weight model) across the @hf.co ecosystem. The latest Transformers now integrates support for the kernels package and uses kernels from the HF Kernel Hub to run models like GPT OSS as fast as possible. 🚀
huggingface.co/blog/welcome...
huggingface.co/blog/welcome...
Transformers 4.54.0 is out! This release adds support for compute kernels hosted on the Hub. When enabled, transformers can replace PyTorch layer implementations by fast, specialized kernels from the hub.
github.com/huggingface/...
github.com/huggingface/...
Release v4.54.0: Kernels, Transformers Serve, Ernie, Voxtral, LFM2, DeepSeek v2, ModernBERT Decoder... · huggingface/transformers
Important news!
In order to become the source of truth, we recognize that we need to address two common and long-heard critiques about transformers:
transformers is bloated
transformers is slow
O...
github.com
July 26, 2025 at 11:34 AM
Transformers 4.54.0 is out! This release adds support for compute kernels hosted on the Hub. When enabled, transformers can replace PyTorch layer implementations by fast, specialized kernels from the hub.
github.com/huggingface/...
github.com/huggingface/...
Reposted by Daniël de Kok
Just released a new version of mktestdocs. It now also supports huggingface docstrings!
github.com/koaning/mkt...
github.com/koaning/mkt...
GitHub - koaning/mktestdocs: Run pytest against markdown files/docstrings.
Run pytest against markdown files/docstrings. Contribute to koaning/mktestdocs development by creating an account on GitHub.
github.com
July 26, 2025 at 10:00 AM
Just released a new version of mktestdocs. It now also supports huggingface docstrings!
github.com/koaning/mkt...
github.com/koaning/mkt...
Reposted by Daniël de Kok
Some of the ModernBERT team is back with new encoder models: Ettin, ranging from tiny to small: 17M, 32M, 68M, 150M, 400M & 1B parameters. They also trained decoder models & checked if decoders could classify & if encoders could generate.
Details in 🧵:
Details in 🧵:
July 17, 2025 at 3:23 PM
Some of the ModernBERT team is back with new encoder models: Ettin, ranging from tiny to small: 17M, 32M, 68M, 150M, 400M & 1B parameters. They also trained decoder models & checked if decoders could classify & if encoders could generate.
Details in 🧵:
Details in 🧵:
Reposted by Daniël de Kok
So excited to finally release our first robot today: Reachy Mini
A dream come true: cute and low priced, hackable yet easy to use, powered by open-source and the infinite community.
Read more and order now at huggingface.co/blog/reachy-...
A dream come true: cute and low priced, hackable yet easy to use, powered by open-source and the infinite community.
Read more and order now at huggingface.co/blog/reachy-...
Your open-source companion - Reachy Mini
YouTube video by Pollen Robotics
youtu.be
July 9, 2025 at 10:09 AM
So excited to finally release our first robot today: Reachy Mini
A dream come true: cute and low priced, hackable yet easy to use, powered by open-source and the infinite community.
Read more and order now at huggingface.co/blog/reachy-...
A dream come true: cute and low priced, hackable yet easy to use, powered by open-source and the infinite community.
Read more and order now at huggingface.co/blog/reachy-...
Reposted by Daniël de Kok
SUSE has released Cavil-Qwen3-4B, a fine-tuned, #opensource #LLM on #HuggingFace. Built to detect #legal text like license declarations, it empowers #devs to stay #compliant. #fast #efficiently. #openSUSE #AI #Licenses news.opensuse.org/2025/06/24/s...
SUSE Refines, Releases Open-Source LLM to Fuel Community Collaboration
Today, SUSE has released a new fine-tuned version of the language model, Cavil-Qwen3-4B, as open source on openSUSE’s Hugging Face in order to make legal com...
news.opensuse.org
June 24, 2025 at 1:59 PM
SUSE has released Cavil-Qwen3-4B, a fine-tuned, #opensource #LLM on #HuggingFace. Built to detect #legal text like license declarations, it empowers #devs to stay #compliant. #fast #efficiently. #openSUSE #AI #Licenses news.opensuse.org/2025/06/24/s...
Over the past few months, we have worked on the @hf.co Kernel Hub. Kernel Hub allows you to get cutting-edge compute kernels directly from the hub in a few lines of code.
David Holz made a great writeup of how you can use kernels in your projects: huggingface.co/blog/hello-h...
David Holz made a great writeup of how you can use kernels in your projects: huggingface.co/blog/hello-h...
Learn the Hugging Face Kernel Hub in 5 Minutes
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
June 17, 2025 at 7:47 AM
Over the past few months, we have worked on the @hf.co Kernel Hub. Kernel Hub allows you to get cutting-edge compute kernels directly from the hub in a few lines of code.
David Holz made a great writeup of how you can use kernels in your projects: huggingface.co/blog/hello-h...
David Holz made a great writeup of how you can use kernels in your projects: huggingface.co/blog/hello-h...
Reposted by Daniël de Kok
Hi Berlin people! @hugobowne.bsky.social is in town & we're celebrating by hosting a meetup together 🎉 This one is all about building with AI & we'll also open the floor for lightning talks. If you're around, come hang out with us!
📆 June 16, 18:00
📍 Native Instruments (Kreuzberg)
🎟️ lu.ma/d53y9p2u
📆 June 16, 18:00
📍 Native Instruments (Kreuzberg)
🎟️ lu.ma/d53y9p2u
June 2, 2025 at 7:48 AM
Hi Berlin people! @hugobowne.bsky.social is in town & we're celebrating by hosting a meetup together 🎉 This one is all about building with AI & we'll also open the floor for lightning talks. If you're around, come hang out with us!
📆 June 16, 18:00
📍 Native Instruments (Kreuzberg)
🎟️ lu.ma/d53y9p2u
📆 June 16, 18:00
📍 Native Instruments (Kreuzberg)
🎟️ lu.ma/d53y9p2u
TGI v3.3.1 is released! This version switches to Torch 2.7 and CUDA 12.8. This should improve support for GPUs with compute capabilities 10.0 (B200) and 12.0 (RTX50x0 and NVIDIA RTX PRO Blackwell GPUs).
github.com/huggingface/...
github.com/huggingface/...
Release v3.3.1 · huggingface/text-generation-inference
This release updates TGI to Torch 2.7 and CUDA 12.8.
What's Changed
change HPU warmup logic: seq length should be with exponential growth by @kaixuanliu in #3217
adjust the round_up_seq logic to a...
github.com
May 22, 2025 at 1:40 PM
TGI v3.3.1 is released! This version switches to Torch 2.7 and CUDA 12.8. This should improve support for GPUs with compute capabilities 10.0 (B200) and 12.0 (RTX50x0 and NVIDIA RTX PRO Blackwell GPUs).
github.com/huggingface/...
github.com/huggingface/...
We just released text-generation-inference 3.3.0. This release adds prefill chunking for VLMs 🚀. We have also Gemma 3 faster & use less VRAM by switching to flashinfer for prefills with images.
github.com/huggingface/...
github.com/huggingface/...
Release v3.3.0 · huggingface/text-generation-inference
Notable changes
Prefill chunking for VLMs.
What's Changed
Fixing Qwen 2.5 VL (32B). by @Narsil in #3157
Fixing tokenization like https://github.com/huggingface/text-embeddin… by @Narsil in #3156...
github.com
May 9, 2025 at 3:39 PM
We just released text-generation-inference 3.3.0. This release adds prefill chunking for VLMs 🚀. We have also Gemma 3 faster & use less VRAM by switching to flashinfer for prefills with images.
github.com/huggingface/...
github.com/huggingface/...
Reposted by Daniël de Kok
The entire Xet team is so excited to bring Llama 4 to the @hf.co community. Every byte downloaded comes through our infrastructure ❤️ 🤗 ❤️ 🤗 ❤️ 🤗
Read the whole post to see more about these models.
Read the whole post to see more about these models.
Welcome Llama 4 Maverick & Scout on Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
huggingface.co
April 5, 2025 at 8:05 PM
The entire Xet team is so excited to bring Llama 4 to the @hf.co community. Every byte downloaded comes through our infrastructure ❤️ 🤗 ❤️ 🤗 ❤️ 🤗
Read the whole post to see more about these models.
Read the whole post to see more about these models.
Reposted by Daniël de Kok
Gemma 3 is live 🔥
You can deploy it from endpoints directly with an optimally selected hardware and configurations.
Give it a try 👇
You can deploy it from endpoints directly with an optimally selected hardware and configurations.
Give it a try 👇
March 12, 2025 at 11:28 AM
Gemma 3 is live 🔥
You can deploy it from endpoints directly with an optimally selected hardware and configurations.
Give it a try 👇
You can deploy it from endpoints directly with an optimally selected hardware and configurations.
Give it a try 👇
HuggingChat keycap sticker when?
March 11, 2025 at 3:48 PM
HuggingChat keycap sticker when?
Reposted by Daniël de Kok
We're thrilled to announce that development of the Orion Browser for Linux has officially started!
Register here to receive news and early access opportunities throughout the development year: forms.kagi.com?q=orion_linu...
Register here to receive news and early access opportunities throughout the development year: forms.kagi.com?q=orion_linu...
March 7, 2025 at 12:56 AM
We're thrilled to announce that development of the Orion Browser for Linux has officially started!
Register here to receive news and early access opportunities throughout the development year: forms.kagi.com?q=orion_linu...
Register here to receive news and early access opportunities throughout the development year: forms.kagi.com?q=orion_linu...
Reposted by Daniël de Kok
want to try QwQ-32B? it just landed on HuggingChat!
March 6, 2025 at 8:06 PM
want to try QwQ-32B? it just landed on HuggingChat!
Reposted by Daniël de Kok
Six months after joining @hf.co we’re kicking off the first migrations from LFS -> Xet backed storage for a handful of repos on the Hugging Face Hub.
A few months ago, I published a timeline of our work and this is a big step (of many!) to bring our storage to the Hub - more in 🧵👇
A few months ago, I published a timeline of our work and this is a big step (of many!) to bring our storage to the Hub - more in 🧵👇
The year is wrapping up and the first pieces of the Xet Team's infrastructure are moving to prod.
We've done a lot of work since joining @hf.co, and I wanted to share a reading guide to see our progress since we got here.
We've done a lot of work since joining @hf.co, and I wanted to share a reading guide to see our progress since we got here.
xet-team (Xet Team)
Org profile for Xet Team on Hugging Face, the AI community building the future.
huggingface.co
February 21, 2025 at 3:22 AM
Six months after joining @hf.co we’re kicking off the first migrations from LFS -> Xet backed storage for a handful of repos on the Hugging Face Hub.
A few months ago, I published a timeline of our work and this is a big step (of many!) to bring our storage to the Hub - more in 🧵👇
A few months ago, I published a timeline of our work and this is a big step (of many!) to bring our storage to the Hub - more in 🧵👇
Reposted by Daniël de Kok
Followers gezocht. Nu we niet meer actief zijn op X (algemeen FS-account 150k followers) en Mastodon helaas niet het volume van het oude Twitter lijkt te krijgen, hoop ik dat BlueSky die plaats kan innemen. Social media is toch een goedkope manier om publiek te informeren. pls rt
February 7, 2025 at 5:16 PM
Followers gezocht. Nu we niet meer actief zijn op X (algemeen FS-account 150k followers) en Mastodon helaas niet het volume van het oude Twitter lijkt te krijgen, hoop ik dat BlueSky die plaats kan innemen. Social media is toch een goedkope manier om publiek te informeren. pls rt
Not only is DeepSeek R1 open, you can now run it on your own hardware with Text Generation Inference 3.1.0.
Awesome work by @mohit-sharma.bsky.social and @narsilou.bsky.social !
Awesome work by @mohit-sharma.bsky.social and @narsilou.bsky.social !
Want to run Deepseek R1 ?
Text-generation-inference v3.1.0 is out and supports it out of the box.
Both on AMD and Nvidia !
Text-generation-inference v3.1.0 is out and supports it out of the box.
Both on AMD and Nvidia !
February 3, 2025 at 10:56 AM
Not only is DeepSeek R1 open, you can now run it on your own hardware with Text Generation Inference 3.1.0.
Awesome work by @mohit-sharma.bsky.social and @narsilou.bsky.social !
Awesome work by @mohit-sharma.bsky.social and @narsilou.bsky.social !
Reposted by Daniël de Kok
Want to run Deepseek R1 ?
Text-generation-inference v3.1.0 is out and supports it out of the box.
Both on AMD and Nvidia !
Text-generation-inference v3.1.0 is out and supports it out of the box.
Both on AMD and Nvidia !
January 31, 2025 at 2:25 PM
Want to run Deepseek R1 ?
Text-generation-inference v3.1.0 is out and supports it out of the box.
Both on AMD and Nvidia !
Text-generation-inference v3.1.0 is out and supports it out of the box.
Both on AMD and Nvidia !