Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up

All HF Hub posts

tomaarsenย 
posted an update 2 days ago
view post
Post
2408
๐Ÿค— Sentence Transformers is joining Hugging Face! ๐Ÿค— This formalizes the existing maintenance structure, as I've personally led the project for the past two years on behalf of Hugging Face! Details:

Today, the Ubiquitous Knowledge Processing (UKP) Lab is transferring the project to Hugging Face. Sentence Transformers will remain a community-driven, open-source project, with the same open-source license (Apache 2.0) as before. Contributions from researchers, developers, and enthusiasts are welcome and encouraged. The project will continue to prioritize transparency, collaboration, and broad accessibility.

Read our full announcement for more details and quotes from UKP and Hugging Face leadership: https://huggingface.co/blog/sentence-transformers-joins-hf

We see an increasing wish from companies to move from large LLM APIs to local models for better control and privacy, reflected in the library's growth: in just the last 30 days, Sentence Transformer models have been downloaded >270 million times, second only to transformers.

I would like to thank the UKP Lab, and especially Nils Reimers and Iryna Gurevych, both for their dedication to the project and for their trust in myself, both now and two years ago. Back then, neither of you knew me well, yet you trusted me to take the project to new heights. That choice ended up being very valuable for the embedding & Information Retrieval community, and I think this choice of granting Hugging Face stewardship will be similarly successful.

I'm very excited about the future of the project, and for the world of embeddings and retrieval at large!
mitkoxย 
posted an update 1 day ago
view post
Post
800
Say hello to my little friends! I just unboxed this trio of HP Z2 G1a!

Three is always better than one!
3x AMD Ryzen AI Max+ Pro 395
384GB RAM
24TB of RAID storage
Ubuntu 24.04
ROCm 7.0.2
llama cpp, vLLM and Aibrix

Small, cheap GPUs are about to become the Raspberry Pi of edge AI inference. Sprinkle some kubectl fairy dust on top, and suddenly it's a high-availability, self-healing, cloud-native, enterprise-grade AI cluster camping in a closet.

Make sure you own your AI. AI in the cloud is not aligned with you; itโ€™s aligned with the company that owns it.
sondhiArmย 
posted an update 1 day ago
view post
Post
827
Hello from PyTorch Conference 2025! ๐Ÿ‘‹

The energy is high, and weโ€™re excited to connect with the community to showcase how developers can build high-performance GenAI applications across cloud, mobile, and edge using PyTorch and ExecuTorch.

Visit us at Booth #P1 to explore hands-on demos, join a one-on-one workshop, or catch one of our insightful sessions throughout the day.

https://developer.arm.com/developer-partners/pytorch
branikitaย 
posted an update 2 days ago
view post
Post
2480
With Robonine team we released an open-source 3D-printed parallel gripper designed for robotics applications, compatible with popular budget servos like Feetech STS3215 and Waveshare ST3215.

This precision gripper offers parallel jaw movement, real-time monitoring, and positioning accuracy of ยฑ0.1ยฐ, making it ideal for both robotics enthusiasts and professionals. Complete build cost: Just $69.45โ€“$74.45, with all components available for purchase on Amazon. Direct links are provided in the Bill of Materials on GitHub.

Check out the project on github: https://github.com/roboninecom/3D-Printed-Parallel-Gripper-for-Robotics-Arms

We encourage you to Watch, Fork, and Star the repository to support our open-source initiative and stay updated on future developments. Your feedback is also welcome!
salma-remyxย 
posted an update about 15 hours ago
view post
Post
705
We've built over 10K containerized reproductions of papers from arXiv!

Instead of spending all day trying to build an environment to test that new idea, just pull the Docker container from the Remyx registry.

And with Remyx, you can start experimenting faster by generating a test PR in your codebase based on the ideas found in your paper of choice.

Hub: https://hub.docker.com/u/remyxai
Remyx docs: https://docs.remyx.ai/resources/ideate
Coming soon, explore reproduced papers with AG2 + Remyx: https://github.com/ag2ai/ag2/pull/2141
AdinaYย 
posted an update 1 day ago
view post
Post
1694
HunyuanWorld Mirror๐Ÿ”ฅa versatile feed forward model for universal 3D world reconstruction by Tencent

tencent/HunyuanWorld-Mirror

โœจ Any prior in โ†’ 3D world out
โœจ Mix camera, intrinsics, depth as priors
โœจ Predict point clouds, normals, Gaussians & more in one pass
โœจ Unified architecture for all 3D task
mitkoxย 
posted an update 3 days ago
view post
Post
2675
I see all Chinese labs are turning TL;DR into TL;DRGB

Problem: 1M text tokens == 1 M opportunities for your GPU to file worker-comp
Solution: donโ€™t feed the model War & Peaceโ€”feed it the movie poster.

This is Glyph, Zaiโ€™s new visual-text compression voodoo:
โ€ข 10 k words โ†’ 3 PNGs โ‰ˆ 3 k visual tokens
โ€ข Compression ratio: 4.3ร—
โ€ข Throughput: 40-60 tok/s i.e. your context window now finishes before my coffee does

So I did the only reasonable thing: asked GLM-4.6 to port Glyph for Qwen3-VL-8B-Thinking.
Translation: I made one model compress a novel into a comic strip, then made another model read the comic strip and still ace QA.
Itโ€™s basically passing notes in class, except the note is a 1920ร—1080 meme and the teacher is a transformer.

We've gone from "Attention is All You Need" to "Attention is Too Expensive, Just Use Your Eyes." Remember kids: in 2025 literacy is optional, but JPEG is forever.
anditoย 
posted an update 3 days ago
view post
Post
1449
Finally, our new paper is out! "๐—™๐—ถ๐—ป๐—ฒ๐—ฉ๐—ถ๐˜€๐—ถ๐—ผ๐—ป: ๐—ข๐—ฝ๐—ฒ๐—ป ๐——๐—ฎ๐˜๐—ฎ ๐—œ๐˜€ ๐—”๐—น๐—น ๐—ฌ๐—ผ๐˜‚ ๐—ก๐—ฒ๐—ฒ๐—ฑ"! ๐Ÿฅณ
FineVision: Open Data Is All You Need (2510.17269)

If you've ever trained a VLM, you know this problem: nobody shares their data mixtures. It's a black box, making replicating SOTA work impossible.
We wanted to change that.

FineVision unifies 200 sources into 24 million samples. With 17.3 million images and 9.5 billion answer tokens, it's the largest open resource of its kind.

In the paper, we share how we built it:
๐Ÿ” finding and cleaning data at scale
๐Ÿงน removing excessive duplicates across sources
๐Ÿค— decontaminating against 66 public benchmarks

My favorite part is Figure 6 (in the video!). It's our visual diversity analysis. It shows that FineVision isn't just bigger; it's more balanced and conceptually richer than other open datasets.
NVIDIA's Eagle 2 paper highlighted just how critical this visual diversity is, and our results confirm it: models trained on FineVision consistently outperform those trained on any other open dataset on 11 benchmarks!

๐ŸŽ‰ To celebrate the paper, Iโ€™m also releasing a concatenated and shuffled version of the full dataset! ๐Ÿ‘‰HuggingFaceM4/FineVision_full_shuffled

Itโ€™s ready to stream, so you can start training your own models right away:

from datasets import load_dataset
d = load_dataset("HuggingFaceM4/FineVision_full_shuffled", split="train", streaming=True)
print(next(iter(d)))

A big shoutout to the first authors: Luis Wiedmann and Orr Zohar. They are rockstars!
piercusย 
posted an update 3 days ago
view post
Post
1778
๐Ÿšง Reproducing LBM-Eraserโ€ฆ in progress! [1]

When repurposing a T2I model into a pure I2I model, thereโ€™s always that orphaned text path โ€” what do we do with it? ๐Ÿค”

You can reuse it as learnable embeddings in multi-task setups [2], freeze an empty text prompt, distillate or prune the corresponding part.

In LBM, they take a clever route โ€” zeroing [3] and reshaping [4] the text-related cross-attentions into self-attentions.
This gives you fresh weights for I2I computation, nicely integrated into your SD architecture.

๐Ÿ“Ž References
[1] Our LBM Fork: https://github.com/finegrain-ai/LBM
[2] OmniPaint: OmniPaint: Mastering Object-Oriented Editing via Disentangled Insertion-Removal Inpainting (2503.08677)
[3] LBM Zeroing: https://github.com/gojasper/LBM/blob/cafebc46a9ac16dcc61691d289cc4676b5c75380/examples/training/train_lbm_surface.py#L147-L148
[4] LBM Reshaping: https://github.com/gojasper/LBM/blob/cafebc46a9ac16dcc61691d289cc4676b5c75380/examples/training/train_lbm_surface.py#L100
umarbutlerย 
posted an update 6 days ago
view post
Post
2819
I'm excited to announce the release of Kanon 2 Embedder, the world's best legal embedding model, ranked first on the Massive Legal Embedding Benchmark ๐ŸŽ‰

This model is the product of quite literally months of painstaking work alongside @abdurrahmanbutler collecting, cleaning, and processing terabytes of data as well as coming up with novel improvements to the standard embedder training recipe to push the limits of what's possible.

Kanon 2 Embedder is my most advanced model to date. On MLEB, it benchmarks as 9% more accurate than OpenAI's best embedding model and 30% faster.

Even when truncated from 1,792 to 768 dimensions, Kanon 2 Embedder continues to hold the number one spot on MLEB.

Importantly, Kanon 2 Embedder is also privacy and security friendly โ€” unlike Voyage, Cohere and Jina, none of your data is used to train our models by default.

Kanon 2 Embedder can also be self-hosted for enterprises with heightened security or reliability requirements.

You can read the full announcement on our blog to learn how we did it and how you can get started using Kanon 2 Embedder to embed your own legal documents: https://isaacus.com/blog/introducing-kanon-2-embedder
  • 2 replies
ยท