Feyn

Intelligence shaped by you

[Feyn @FeynAI]

https://t.co/ieGNPaDBMI

[Feyn @FeynAI]

Building FeyNoBg also exposed a tooling problem. Image matting models usually live in isolated repos with different interfaces.

So we built NoBg, a Python library for running, training models, and evaluating image mating models. Currently, it supports BiRefNet with more architectures coming. We hope you use it to build something exciting.

https://t.co/eWHc0MJcdI

[Feyn @FeynAI]

FeyNoBg and NoBg are both open source.

- Model: https://t.co/PXDqLDhQ7Q
- Try it: https://t.co/EGR4vpC3Jr
- NoBg Library: https://t.co/fO2rqOhz9y
- Technical Blog: https://t.co/XwCsRypHic

[Feyn @FeynAI]

We’re releasing FeyNoBg, our open-source model for image background removal.

Across eight benchmarks, it sets the best published S-measure on four and comes within 2% of the leader on the rest.

Try it out: https://t.co/EGR4vpC3Jr

[Feyn @FeynAI]

Building FeyNoBg also exposed a tooling problem. Image matting models usually live in isolated repos with different interfaces.

So we built NoBg, a Python library for running, training models, and evaluating image mating models. Currently, it supports BiRefNet with more architectures coming. We hope you use it to build something exciting.

https://t.co/eWHc0MJcdI

[Feyn @FeynAI]

To develop SQRL, we first trained SQRL-35B-A3B as the teacher, then distilled its successful inspection trajectories into smaller 4B and 9B models.

Read more about how we developed SQRL: https://t.co/KaFpVC7NqF

[Feyn @FeynAI]

https://t.co/qyJZrVqZj1

[Feyn @FeynAI]

We’re introducing SQRL, a family of small text-to-SQL models.

On the BIRD Dev benchmark, SQRL's 35B, 9B, and 4B models beat Claude Opus on SQL execution accuracy.

[Feyn @FeynAI]

SQRL is open source and available on Hugging Face. The 9B model is our recommended default.

https://t.co/PNRX4rCTq3

[Feyn @FeynAI]

https://t.co/qyJZrVqZj1

[Feyn @FeynAI]

Pulpie is open source and available on Hugging Face today. See our article to get started and for more details on how we built Pulpie.

https://t.co/wMZbwt5xXV

[Feyn @FeynAI]

https://t.co/akJQtdsXeM

[Feyn @FeynAI]

Introducing Pulpie, models for cleaning the web.

70% of a typical HTML page is ads, navigation, and sidebars. Pulpie removes this noise and returns a clean document you can use in pre-training or as context.

Previously, cleaning 1 billion pages with the best extractors cost $159,000. Pulpie brings that down to $7,900. A 20x decrease.

[Feyn @FeynAI]

The gains are architectural.

Today's best extractors are decoders limited by memory bandwidth. Pulpie is an encoder bound by compute.

GPUs are starved for bandwidth, not compute. As a result, Pulpie is performant everywhere. Our testing shows Pulpie to be 7x faster on A100, and 20x faster on L4 GPUs.

[Feyn @FeynAI]

https://t.co/akJQtdsXeM

[Feyn @FeynAI]

🔥🚀Chonkie 1.6.8 is out with PyEmscripten wheels!
🐍You can now run the full Python Chonkie library directly in your browser using Pyodide🦛

This is an early release that brings Chonkie’s core functionality to the web, but it's a big step towards 𝕓𝕣𝕠𝕨𝕤𝕖𝕣 𝕟𝕒𝕥𝕚𝕧𝕖 𝕡𝕪𝕥𝕙𝕠𝕟 𝕔𝕙𝕦𝕟𝕜𝕚𝕟𝕘.

We’d love to hear your feedback! try it out and let us know what works, what doesn't, and what you'd like to see next!

Happy coding! 🦛✨

[Lain (🦛/acc) @not_so_lain]

Happy to share that @ChonkieAI just crossed 4K GitHub stars and 4 million PyPI downloads! 🎉
from a small side project to a fast growing library used by millions.
Huge thanks to the community, so stay tuned as bigger things are coming 🔥

[Feyn @FeynAI]

@TeraflopAI You can also check out this excellent blog post by @EnricoShippole where he breaks down what you can build on top of this:

🔗 https://t.co/mH9rzhX9iv

Highly recommended if you want to see the real possibilities 👀

[Feyn @FeynAI]

🐦‍⬛+🦛 = 🔥
You can now leverage @TeraflopAI directly inside the Chonkie ecosystem.
Seamless integration, zero friction. Just pure power.
Check the post below for all the details 👇

[TeraflopAI @TeraflopAI]

We are happy to announce our official integration into @ChonkieAI. You can now use @TeraflopAI’s powerful text segmentation API directly within the Chonkie open-source library to chunk text seamlessly at scale.