julien-c (Julien Chaumond)

reacted to jsulz's post with 🔥 18 days ago

Post

2131

xet-team at Hugging face was wondering if you wanted to join the fun and jump over to Xet storage. 🤗

We've been onboarding folks https://huggingface.co/blog/xet-on-the-hub know the backend can scale (Llama 4 and Qwen 3 are on Xet), is great for working with quants (see xet-team/quantization-dedup ), and we're pushing on inviting impactful orgs and users on the Hub. You fit the bill.

We'd love to onboard you, get some feedback, and create some excitement 🎉

The steps are pretty straightforward - join the waitlist at hf.co/join/xet and we'll take care of the rest.

The system is fully backward compatible, so you shouldn't notice a thing. BUT to get the best experience when uploading/downloading, make sure you have hf_xet installed alongside the latest huggingface_hub

What do you think?

4 replies

·

reacted to reach-vb's post with 👍 19 days ago

Post

3690

hey hey @mradermacher - VB from Hugging Face here, we'd love to onboard you over to our optimised xet backend! 💥

as you know we're in the process of upgrading our storage backend to xet (which helps us scale and offer blazingly fast upload/ download speeds too): https://huggingface.co/blog/xet-on-the-hub and now that we are certain that the backend can scale with even big models like Llama 4/ Qwen 3 - we;re moving to the next phase of inviting impactful orgs and users on the hub over as you are a big part of the open source ML community - we would love to onboard you next and create some excitement about it in the community too!

in terms of actual steps - it should be as simple as one of the org admins to join hf.co/join/xet - we'll take care of the rest.

p.s. you'd need to have a the latest hf_xet version of huggingface_hub lib but everything else should be the same: https://huggingface.co/docs/hub/storage-backends#using-xet-storage

p.p.s. this is fully backwards compatible so everything will work as it should! 🤗

16 replies

·

replied to cbensimon's post 22 days ago

WOOHOO!!

reacted to cbensimon's post with 🔥 22 days ago

Post

5745

🚀 ZeroGPU medium size is now available as a power-user feature

Nothing too fancy for now—ZeroGPU Spaces still default to large (70GB VRAM)—but this paves the way for:
- 💰 size-based quotas / pricing (medium will offer significantly more usage than large)
- 🦣 the upcoming xlarge size (141GB VRAM)

You can as of now control GPU size via a Space variable. Accepted values:
- auto (future default)
- medium
- large (current default)

The auto mode checks total CUDA tensor size during startup:
- More than 30GB → large
- Otherwise → medium

3 replies

·

replied to their post about 1 month ago

did you get it to work since?

reacted to their post with 👍🚀🔥 about 1 month ago

Post

3894

Important notice 🚨

For Inference Providers who have built support for our Billing API (currently: Fal, Novita, HF-Inference – with more coming soon), we've started enabling Pay as you go (=PAYG)

What this means is that you can use those Inference Providers beyond the free included credits, and they're charged to your HF account.

You can see it on this view: any provider that does not have a "Billing disabled" badge, is PAYG-compatible.

9 replies

·

reacted to danielhanchen's post with ❤️🤗🔥 about 1 month ago

Post

5826

🦥 Introducing Unsloth Dynamic v2.0 GGUFs!
Our v2.0 quants set new benchmarks on 5-shot MMLU and KL Divergence, meaning you can now run & fine-tune quantized LLMs while preserving as much accuracy as possible.

Llama 4: unsloth/Llama-4-Scout-17B-16E-Instruct-GGUF
DeepSeek-R1: unsloth/DeepSeek-R1-GGUF-UD
Gemma 3: unsloth/gemma-3-27b-it-GGUF

We made selective layer quantization much smarter. Instead of modifying only a subset of layers, we now dynamically quantize all layers so every layer has a different bit. Now, our dynamic method can be applied to all LLM architectures, not just MoE's.

Blog with Details: https://docs.unsloth.ai/basics/dynamic-v2.0

All our future GGUF uploads will leverage Dynamic 2.0 and our hand curated 300K–1.5M token calibration dataset to improve conversational chat performance.

For accurate benchmarking, we built an evaluation framework to match the reported 5-shot MMLU scores of Llama 4 and Gemma 3. This allowed apples-to-apples comparisons between full-precision vs. Dynamic v2.0, QAT and standard iMatrix quants.

Dynamic v2.0 aims to minimize the performance gap between full-precision models and their quantized counterparts.

reacted to their post with 😎🤗🔥 about 1 month ago

Post

4765

BOOOOM: Today I'm dropping TINY AGENTS

the 50 lines of code Agent in Javascript 🔥

I spent the last few weeks working on this, so I hope you will like it.

I've been diving into MCP (Model Context Protocol) to understand what the hype was all about.

It is fairly simple, but still quite powerful: MCP is a standard API to expose sets of Tools that can be hooked to LLMs.

But while doing that, came my second realization:

Once you have a MCP Client, an Agent is literally just a while loop on top of it. 🤯

➡️ read it exclusively on the official HF blog: https://huggingface.co/blog/tiny-agents

1 reply

·

posted an update about 1 month ago

Post

4765

BOOOOM: Today I'm dropping TINY AGENTS

the 50 lines of code Agent in Javascript 🔥

I spent the last few weeks working on this, so I hope you will like it.

I've been diving into MCP (Model Context Protocol) to understand what the hype was all about.

It is fairly simple, but still quite powerful: MCP is a standard API to expose sets of Tools that can be hooked to LLMs.

But while doing that, came my second realization:

Once you have a MCP Client, an Agent is literally just a while loop on top of it. 🤯

➡️ read it exclusively on the official HF blog: https://huggingface.co/blog/tiny-agents

1 reply

·

replied to gtvracer's post about 2 months ago

which provider do you use?

We'll ship a provider="auto" in the coming days BTW, cc @sbrandeis @Wauplin @celinah

In the meantime, the model is served by those providers, you can use one of them, for instance, add provider="novita" to your code:

replied to OFT's post 2 months ago

Hey, things have been in flux somewhat, but they should stabilize now. Sorry about the moving parts!

More details, from @michellehbn :

In February, Inference billing usage had been a fixed rate while we added pay-as-you-go support so now, usage in March on takes into account compute time x price of the hardware. We're really sorry for any confusion or scare! We have more information about Inference Providers here: https://huggingface.co/docs/inference-providers/en/index

replied to jsulz's post 3 months ago

it's definitely the future:)

reacted to jsulz's post with ❤️🚀 3 months ago

Post

1462

It's finally here ❤️

Build faster than ever with lightning fast upload and download speeds starting today on the Hub ⚡

Xet storage is rolling out access across the Hub - join the waitlist here https://huggingface.co/join/xet

You can apply for yourself, or your entire organization. Head over to your account settings for more information or join anywhere you see the Xet logo on a repository you know.

Have questions? Join the conversation below 👇 or open a discussion on the Xet team page xet-team/README

6 replies

·

Julien Chaumond PRO

AI & ML interests

Recent Activity

Organizations

julien-c's activity