🦜 Xenova / @xenovacom
@xcancel.com.xenovacom@rss-parrot.net
I'm an automated parrot! I relay a website's RSS feed to the Fediverse. Every time a new post appears in the feed, I toot about it. Follow me to get all new posts in your Mastodon timeline!
Brought to you by the RSS Parrot.
---
Twitter feed for: @xenovacom. Generated by xcancel.com
Your feed and you don't want it here? Just
e-mail the birb.
RT by @xenovacom: You can run Gemma 4 100% locally in your browser thanks to HF transformers.js. That means 100% private and 100% free!
@xenovacom created a demo for it here: https://huggingface.co/spaces/webml-community/Gemma-4-WebGPU
https://rss.xcancel.com/ClementDelangue/status/2039782910996148508#m
Published: April 2, 2026 19:11
You can run Gemma 4 100% locally in your browser thanks to HF transformers.js. That means 100% private and 100% free!
@xenovacom created a demo for it here: huggingface.co/spaces/webml-…
R to @xenovacom: Demo powered by Transformers.js! 🤗
Try it out yourself! 👇
https://huggingface.co/spaces/webml-community/Gemma-4-WebGPU
https://rss.xcancel.com/xenovacom/status/2039741228225351999#m
Published: April 2, 2026 16:26
Demo powered by Transformers.js! 🤗
Try it out yourself! 👇
huggingface.co/spaces/webml-…
NEW: Google releases Gemma 4, their most capable open models yet! 🤯 Apache-2.0, multimodal (text, image, and audio input), and multilingual (140 languages)!
They can even run 100% locally in your browser on WebGPU. Watch it describe the Artemis II launch! 🚀
Try the demo! 👇
https://rss.xcancel.com/xenovacom/status/2039741226337935430#m
Published: April 2, 2026 16:26
NEW: Google releases Gemma 4, their most capable open models yet! 🤯 Apache-2.0, multimodal (text, image, and audio input), and multilingual (140 languages)!
They can even run 100% locally in your browser on WebGPU. Watch it describe the Artemis II launch!…
What if AI chat interfaces had gravity?
https://rss.xcancel.com/xenovacom/status/2039372763081719988#m
Published: April 1, 2026 16:02
What if AI chat interfaces had gravity?
Video
R to @xenovacom: Yes, this is a real demo you can play around with! 😂 We're running @LiquidAI's new LFM2.5-350M in-browser with Transformers.js! 🤗
https://huggingface.co/spaces/webml-community/april-fools-2026
https://rss.xcancel.com/xenovacom/status/2039372764721664274#m
Published: April 1, 2026 16:02
Yes, this is a real demo you can play around with! 😂 We're running @LiquidAI's new LFM2.5-350M in-browser with Transformers.js! 🤗
huggingface.co/spaces/webml-…
R to @xenovacom: Huge congrats to @LiquidAI on the release! I can't wait to see what the community builds with it.
Try out the 🤗 Transformers.js demo!
https://huggingface.co/spaces/webml-community/lfm2.5-webgpu-summarizer
https://xcancel.com/xenovacom/status/2039043412385521835#m
Published: March 31, 2026 18:13
Huge congrats to @LiquidAI on the release! I can't wait to see what the community builds with it.
Try out the 🤗 Transformers.js demo!
huggingface.co/spaces/webml-…
R to @xenovacom: The model builds on their previous generation, with additional pre-training (10T → 28T) and large-scale RL, allowing it to outperform other models of similar size. 😍
It's also extremely fast thanks to the LFM2 architecture (hybrid convolution and attention blocks)!
https://xcancel.com/xenovacom/status/2039043409512468671#m
Published: March 31, 2026 18:13
The model builds on their previous generation, with additional pre-training (10T → 28T) and large-scale RL, allowing it to outperform other models of similar size. 😍
It's also extremely fast thanks to the LFM2 architecture (hybrid convolution and…
NEW: LiquidAI just released LFM2.5-350M, a tiny model that brings agentic AI and tool-calling capabilities to resource-constrained environments. 🤯
It can even run locally in your browser via WebGPU, serving as a powerful companion while you browse the web.
Try the demo! 👇
https://xcancel.com/xenovacom/status/2039043406823833964#m
Published: March 31, 2026 18:13
NEW: LiquidAI just released LFM2.5-350M, a tiny model that brings agentic AI and tool-calling capabilities to resource-constrained environments. 🤯
It can even run locally in your browser via WebGPU, serving as a powerful companion while you browse the…
Pinned: Introducing 🤗 Transformers.js v4: state-of-the-art machine learning for the web!
🚀 New WebGPU backend (browser, Node.js, Bun, Deno)
⚡️ Huge performance improvements
🤯 Support for over 200 architectures
🛠️ Complete codebase refactor
Learn more about our biggest release yet! 👇
https://xcancel.com/xenovacom/status/2038610331417608691#m
Published: March 30, 2026 13:32
Introducing 🤗 Transformers.js v4: state-of-the-art machine learning for the web!
🚀 New WebGPU backend (browser, Node.js, Bun, Deno)
⚡️ Huge performance improvements
🤯 Support for over 200 architectures
🛠️ Complete codebase refactor
Learn more about our…
R to @xenovacom: Get started with
npm i @huggingface/transformers
Links:
📖 Blog post: https://huggingface.co/blog/transformersjs-v4
📝Release notes: https://github.com/huggingface/transformers.js/releases/tag/4.0.0
🛝 Demos: https://huggingface.co/collections/webml-community/transformersjs-v4-demos
🔗 Release video: https://youtu.be/KnhppkY4gHs?si=2wGHOmfzhRjwtAK7
https://xcancel.com/xenovacom/status/2038610334219395102#m
Published: March 30, 2026 13:32
Get started with
npm i @huggingface/transformers
Links:
📖 Blog post: huggingface.co/blog/transfor…
📝Release notes: github.com/huggingface/trans…
🛝 Demos: huggingface.co/collections/w…
🔗 Release video: youtu.be/KnhppkY4gHs?si=2wGH…