Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Wauplin 
posted an update 2 days ago
Post
1848
‼️ huggingface_hub's v0.30.0 is out with our biggest update of the past two years!

Full release notes: https://github.com/huggingface/huggingface_hub/releases/tag/v0.30.0.

🚀 Ready. Xet. Go!

Xet is a groundbreaking new protocol for storing large objects in Git repositories, designed to replace Git LFS. Unlike LFS, which deduplicates files, Xet operates at the chunk level—making it a game-changer for AI builders collaborating on massive models and datasets. Our Python integration is powered by [xet-core](https://github.com/huggingface/xet-core), a Rust-based package that handles all the low-level details.

You can start using Xet today by installing the optional dependency:

pip install -U huggingface_hub[hf_xet]


With that, you can seamlessly download files from Xet-enabled repositories! And don’t worry—everything remains fully backward-compatible if you’re not ready to upgrade yet.

Blog post: https://huggingface.co/blog/xet-on-the-hub
Docs: https://huggingface.co/docs/hub/en/storage-backends#xet


⚡ Inference Providers

- We’re thrilled to introduce Cerebras and Cohere as official inference providers! This expansion strengthens the Hub as the go-to entry point for running inference on open-weight models.

- Novita is now our 3rd provider to support text-to-video task after Fal.ai and Replicate.

- Centralized billing: manage your budget and set team-wide spending limits for Inference Providers! Available to all Enterprise Hub organizations.

from huggingface_hub import InferenceClient
client = InferenceClient(provider="fal-ai", bill_to="my-cool-company")
image = client.text_to_image(
    "A majestic lion in a fantasy forest",
    model="black-forest-labs/FLUX.1-schnell",
)
image.save("lion.png")


- No more timeouts when generating videos, thanks to async calls. Available right now for Fal.ai, expecting more providers to leverage the same structure very soon!

Hello there. Regarding inference providers, is there an issue with Huggingface's serverless Inference API? My spaces use models that, for some reason, state that they are unavailable to be used by any of the inference providers, despite them working fine two months ago, before you guys started adding support for the 3rd party providers. I also attempted to upload a model myself using a space to convert safetensor files to diffusers for usage on Huggingface, but when I tried to use it in my space, it gave me an error stating No API and something about bools not being iterable. My older spaces also give me JSON decoder errors. I wish to know if you all are aware of this issue and are working towards restoring serverless inference API call functionality in the future.

·

My spaces use models that, for some reason, state that they are unavailable to be used by any of the inference providers, despite them working fine two months ago

The Huggingface's serverless Inference API wasn't a production-ready service. It was only meant to easily experiment and prototype ML apps. We started rolling out inference providers to tackle this topic and make things more future-proof. Regarding the specific problem you have, it's hard to help without knowing the specific models you were using back then. The most likely is that these models have been removed from HF Inference API infra as we are now focusing on making fewer but high-impact models available.

Join the waitlist if you want access to Xet-enabled repos - details here https://huggingface.co/join/xet 🤗