AI & ML interests

None defined yet.

Recent Activity

reach-vbΒ 
posted an update 16 days ago
view post
Post
2249
Excited to onboard FeatherlessAI on Hugging Face as an Inference Provider - they bring a fleet of 6,700+ LLMs on-demand on the Hugging Face Hub 🀯

Starting today, you'd be able to access all those LLMs (OpenAI compatible) on HF model pages and via OpenAI client libraries too! πŸ’₯

Go, play with it today: https://huggingface.co/blog/inference-providers-featherless

P.S. They're also bringing on more GPUs to support all your concurrent requests!
celinahΒ 
posted an update about 1 month ago
view post
Post
2284
✨ Today we’re releasing Tiny Agents in Python β€” an MCP-powered Agent in ~70 lines of code 🐍

Inspired by Tiny Agents in JS from @julien-c , we ported the idea to Python and integrated it directly into huggingface_hub β€” with a built-in MCP Client and a Tiny Agents CLI.

TL;DR: With MCP (Model Context Protocol), you can expose tools like web search or image generation and connect them directly to LLMs. It’s simple β€” and surprisingly powerful.

pip install "huggingface_hub[mcp]>=0.32.0"

We wrote a blog post where we show how to run Tiny Agents, and dive deeper into how they work and how to build your own.
πŸ‘‰ https://huggingface.co/blog/python-tiny-agents

  • 1 reply
Β·
sayakpaulΒ 
posted an update about 1 month ago
view post
Post
2583
Diffusers supports a good variety of quantization backends. It can be challenging to navigate through them, given the complex nature of diffusion pipelines in general.

So, @derekl35 set out to write a comprehensive guide that puts users in the front seat. Explore the different backends we support, learn the trade-offs they offer, and finally, check out the cool space we built that lets you compare quantization results.

Give it a go here:
https://lnkd.in/gf8Pi4-2
sayakpaulΒ 
posted an update about 1 month ago
view post
Post
1710
Despite the emergence of combining LLM and DiT architectures for T2I synthesis, its design remains severely understudied.

This was done long ago and got into CVPR25 -- super excited to finally share it now, along with the data and code β™₯️

We explore several architectural choices that affect this design. We provide an open & reproducible training recipe that works at scale.

Works like Playground v3 have already explored a deep fusion between an LLM and a DiT, sharing their representations through layerwise attention. They exhibit excellent performance on T2I.

Despite its compelling results and other performance virtues, it remains unexplored, which is what we want to improve in our work. Specifically, we take a pre-trained LLM (Gemma-2B) and trainable DiT, and set out to explore what makes a "good deep fusion" between the two for T2I.

We explore several key questions in the work, such as:

Q1: How should we do attention? We considered several alternatives. PixArt-Alpha like attention (cross-attention) is very promising.
Q2: Should we incorporate additional text modulation?
Q3: Can we eliminate timestep conditioning?
Q4: How do we do positional encodings?
Q5: Do instruction-tuned LLMs help deep fusion?
Q6: Would using a decoder LLM from a multimodal model be helpful?
Q7: Does using a better variant of Gemma help?

Based on the above findings, we arrive at FuseDiT with the following components on top of the base architecture from the findings of our experiments.

* No AdaLN-Zero modules
* 1D + 2D-RoPE
* Gemma 2 2B, adjusting DiT configurations accordingly

We trained FuseDiT on a mixture from CC12M, JourneyDB, & SA (~26M image-text pairs) for 800 steps. While not the best model, it's encouraging to develop something in a guided manner using open datasets.

To know more (code, models, all are available), please check out the paper:
https://lnkd.in/gg6qyqZX.
reach-vbΒ 
posted an update about 1 month ago
view post
Post
3990
hey hey @mradermacher - VB from Hugging Face here, we'd love to onboard you over to our optimised xet backend! πŸ’₯

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! πŸ€—
Β·
julien-cΒ 
posted an update 2 months ago
view post
Post
5194
BOOOOM: Today I'm dropping TINY AGENTS

the 50 lines of code Agent in Javascript πŸ”₯

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. 🀯

➑️ read it exclusively on the official HF blog: https://huggingface.co/blog/tiny-agents
  • 1 reply
Β·
WauplinΒ 
posted an update 3 months ago
view post
Post
2227
‼️ 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.

πŸš€ 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 levelβ€”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 worryβ€”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!
Β·
julien-cΒ 
posted an update 4 months ago
view post
Post
3970
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.
Β·
lysandreΒ 
posted an update 4 months ago
view post
Post
7206
SmolVLM-2 and SigLIP-2 are now part of transformers in dedicated releases!

They're added on top of the v4.49.0 release, and can be installed from the following tags: v4.49.0-SmolVLM-2 and v4.49.0-SigLIP-2.

This marks a new beginning for the release process of transformers. For the past five years, we've been doing monthly releases featuring many models (v4.49.0, the latest release, features 9 new architectures).

Starting with SmolVLM-2 & SigLIP2, we'll now additionally release tags supporting new models on a stable branch. These models are therefore directly available for use by installing from the tag itself. These tags will continue to be updated with fixes applied to these models.

Going forward, continue expecting software releases following semantic versioning: v4.50.0 will have ~10 new architectures compared to v4.49.0, as well as a myriad of new features, improvements and bug fixes. Accompanying these software releases, we'll release tags offering brand new models as fast as possible, to make them accessible to all immediately.
  • 1 reply
Β·
sayakpaulΒ 
posted an update 4 months ago
view post
Post
3869
Inference-time scaling meets Flux.1-Dev (and others) πŸ”₯

Presenting a simple re-implementation of "Inference-time scaling diffusion models beyond denoising steps" by Ma et al.

I did the simplest random search strategy, but results can potentially be improved with better-guided search methods.

Supports Gemini 2 Flash & Qwen2.5 as verifiers for "LLMGrading" πŸ€—

The steps are simple:

For each round:

1> Starting by sampling 2 starting noises with different seeds.
2> Score the generations w.r.t a metric.
3> Obtain the best generation from the current round.

If you have more compute budget, go to the next search round. Scale the noise pool (2 ** search_round) and repeat 1 - 3.

This constitutes the random search method as done in the paper by Google DeepMind.

Code, more results, and a bunch of other stuff are in the repository. Check it out here: https://github.com/sayakpaul/tt-scale-flux/ πŸ€—
sayakpaulΒ 
posted an update 5 months ago
view post
Post
2115
We have been cooking a couple of fine-tuning runs on CogVideoX with finetrainers, smol datasets, and LoRA to generate cool video effects like crushing, dissolving, etc.

We are also releasing a LoRA extraction utility from a fully fine-tuned checkpoint. I know that kind of stuff has existed since eternity, but the quality on video models was nothing short of spectacular. Below are some links:

* Models and datasets: finetrainers
* finetrainers: https://github.com/a-r-r-o-w/finetrainers
* LoRA extraction: https://github.com/huggingface/diffusers/blob/main/scripts/extract_lora_from_model.py
  • 1 reply
Β·
sayakpaulΒ 
posted an update 5 months ago
view post
Post
2054
We have authored a post to go over the state of video generation in the Diffusers ecosystem 🧨

We cover the models supported, the knobs of optims our users can fire, fine-tuning, and more πŸ”₯

5-6GBs for HunyuanVideo, sky is the limit 🌌 πŸ€—
https://huggingface.co/blog/video_gen
sayakpaulΒ 
posted an update 6 months ago
view post
Post
4459
Commits speak louder than words πŸ€ͺ

* 4 new video models
* Multiple image models, including SANA & Flux Control
* New quantizers -> GGUF & TorchAO
* New training scripts

Enjoy this holiday-special Diffusers release πŸ€—
Notes: https://github.com/huggingface/diffusers/releases/tag/v0.32.0