18 104 129

Aurélien-Morgan CLAUDON

Aurelien-Morgan

https://huggingface.co/retrain-pipelines

AI & ML interests

None yet

Recent Activity

upvoted a paper 3 days ago

Aya Vision: Advancing the Frontier of Multilingual Multimodality

upvoted a paper 3 days ago

Qwen3 Technical Report

reacted to cbensimon's post with 👀 6 days ago

🚀 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`

View all activity

Organizations

Aurelien-Morgan's activity

reacted to cbensimon's post with 👀 6 days ago

Post

5499

🚀 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

reacted to ordagan's post with ❤️ 6 days ago

Post

2196

Excited to introduce Jamba by AI21
ai21labs/Jamba-v0.1

We are thrilled to announce Jamba, the world’s first production-grade Mamba based model.

Key Features:
- First production-grade Mamba based model built on a novel SSM-Transformer hybrid architecture
- 3X throughput on long contexts compared to Mixtral 8x7B
- Democratizes access to a massive 256K context window
- The only model in its size class that fits up to 140K context on a single GPU

Jamba is based on a novel architecture that combines Mamba and Transformer. While our initial results show great efficiency gains, we expect this to be further explored and improved with the help of the community.

Check out our blog post for more info: https://ai21-labs.webflow.io/blog/announcing-jamba

2 replies

posted an update 8 days ago

Post

369

Hey, I'll be presenting @retrain-pipelines and almighty function-calling at the Hugging Face Paris HQ, you guys.
Monday evening. Lightning-talk style. With AI Tinkerers.

Come hang !

https://paris.aitinkerers.org/p/ai-tinkerers-paris-ai21-labs-takeover-on-may-19th

https://huggingface.co/blog/Aurelien-Morgan/the-almighty-function-caller

posted an update 25 days ago

Post

3132

The Almighty function-caller

How would you like to build smart GenAi infrastructure ?
Give extensive tools memory to your edge agentic system,
And optimize the resources it takes to run yet a high-performance set of agents ?

We came up with a novel approach to function-calling at scale for smart companies and corporate-grade use-cases.

Read our full-fledged blog article on this here on Hugging Face :
https://huggingface.co/blog/Aurelien-Morgan/the-almighty-function-caller

reacted to danielhanchen's post with 🔥 26 days ago

Post

5787

🦥 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.

posted an update 26 days ago

Post

662

retrain-pipelines 0.1.2 finally dropped. It comes with a hot Hugging Face Hub integration. Go check it out. We have 2 articles about it coming up. One already fully written so, be on the lookout !
@retrain-pipelines

Also, I'll be volunteering at GOSIM AI Paris 2025. If you're interested in chatting, hmu.

reacted to jsulz's post with 🧠 about 1 month ago

Post

3195

What does it mean when models share the same bytes?

We've investigated some quants and have seen that a considerable portion of quantizations of the same model share the same bytes and can be deduplicated to save considerable upload time for quantizers on the Hub.

This space where we crack open a repo from @bartowski shows we can get significant dedupe xet-team/quantization-dedup

You can get a sense of why by reading this write-up: https://github.com/bartowski1182/llm-knowledge/blob/main/quantization/quantization.md

But what about finetuned models?

Since going into production the

xet-team has migrated hundreds of repositories on the Hub to our storage layer, including classic "pre-Hub" open-source models like FacebookAI/xlm-roberta-large (XLM-R) from

FacebookAI

XLM-R, introduced in 2019, set new benchmarks for multilingual NLP by learning shared representations across 100 languages. It was then fine-tuned on English, Spanish, Dutch, and German, generating language-specific derivations for each - check out the paper here Unsupervised Cross-lingual Representation Learning at Scale (1911.02116)

These finetunes share much of the same architecture and layout as XLM-R with similar training methods and goals. It makes sense that they would share bytes, but it's still fascinating to see.

We put together a similar space to explore these models to see where they overlap - check it out for yourself xet-team/finetune-dedupe

The darker each block in the heatmap, the more the bytes are shared. Clicking on a repos blocks shows all other repos that share blocks.

1 reply

posted an update about 2 months ago

Post

1996

Almost there !
https://test.pypi.org/project/test-010-retrain-pipelines/

reacted to AdinaY's post with 😎 2 months ago

Post

1468

Step-Video-TI2V 🔥 text driven Image-to-Video Model released by StepFun_ai

Paper:
Step-Video-TI2V Technical Report: A State-of-the-Art Text-Driven Image-to-Video Generation Model (2503.11251)
Model:
stepfun-ai/stepvideo-ti2v

✨ 30B with MIT license
✨ Up to 102 frames from text + image inputs
✨ Supports motion control and anime-style

reacted to jsulz's post with ❤️ 2 months ago

Post

1996

If you've been following along with the Xet Team's (

xet-team ) work, you know we've been working to migrate the Hugging Face Hub from Git LFS and to Xet.

Recently, we launched a waitlist to join the movement to Xet (join here! https://huggingface.co/join/xet ) but getting to this point was a journey.

From the initial proof of concept in August, to launching on the Hub internally, to migrating a set of repositories and routing a small chunk of download traffic on the Hub through our infrastructure. Every step of the way has been full of challenges, big and small, and well worth the effort.

Over the past few weeks, with real traffic flowing through our services we’ve tackled some truly gnarly issues (unusual upload/download patterns, memory leaks, load imbalances, and more) and resolved each without major disruptions.

If you're curious about how this sliver of Hub infrastructure looks as we routed traffic through it for the first time (and want a deep dive full of Grafana and Kibana charts 🤓) I have a post for you.

Here's an inside look into the day of our first migrations and the weeks following, where we pieced together solutions in real time.

https://huggingface.co/blog/xet-on-the-hub

reacted to AdinaY's post with 😎 2 months ago

Post

2156

FlexWorld 🔥 an open framework that generates 3D scenes from a single image!

Model: GSAI-ML/FlexWorld
Paper: FlexWorld: Progressively Expanding 3D Scenes for Flexiable-View Synthesis (2503.13265)

✨ 360° rotation & zooming
✨ High quality novel views powered by video-to-video diffusion model
✨ Progressive 3D expansion

2 replies

replied to jsulz's post 2 months ago

The retrain-pipelines org and I joined the waitlist today. Been looking forward to this for some time. Curious to see the outcome. The promise got me hooked from day 1. The tech as presented does have potential.

reacted to jsulz's post with ❤️ 2 months ago

Post

1456

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

reacted to thomwolf's post with 🚀 2 months ago

Post

2909

We've kept pushing our Open-R1 project, an open initiative to replicate and extend the techniques behind DeepSeek-R1.

And even we were mind-blown by the results we got with this latest model we're releasing: ⚡️OlympicCoder ( open-r1/OlympicCoder-7B and open-r1/OlympicCoder-32B)

It's beating Claude 3.7 on (competitive) programming –a domain Anthropic has been historically really strong at– and it's getting close to o1-mini/R1 on olympiad level coding with just 7B parameters!

And the best part is that we're open-sourcing all about its training dataset, the new IOI benchmark, and more in our Open-R1 progress report #3: https://huggingface.co/blog/open-r1/update-3

Datasets are are releasing:
- open-r1/codeforces
- open-r1/codeforces-cots
- open-r1/ioi
- open-r1/ioi-test-cases
- open-r1/ioi-sample-solutions
- open-r1/ioi-cots
- open-r1/ioi-2024-model-solutions

reacted to julien-c's post with 😎 2 months ago

Post

3818

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

replied to fdaudens's post 2 months ago

You gonna revive the LinkedIn newsletter someday ? Think it was cool 😭😭
https://www.linkedin.com/newsletters/7233909926606053377/

replied to AdinaY's post 3 months ago

Seen many astonishing results from people posting examples of this model in action.

reacted to AdinaY's post with 🤯 3 months ago

Post

2742

Wan2.1 🔥📹 new OPEN video model by Alibaba Wan team!

Model: Wan-AI/Wan2.1-T2V-14B
Demo: Wan-AI/Wan2.1

✨Apache 2.0
✨8.19GB VRAM, runs on most GPUs
✨Multi-Tasking: T2V, I2V, Video Editing, T2I, V2A
✨Text Generation: Supports Chinese & English
✨Powerful Video VAE: Encode/decode 1080P w/ temporal precision

1 reply

reacted to freddyaboulton's post with 🤗🔥 3 months ago

Post

3284

Getting WebRTC and Websockets right in python is very tricky. If you've tried to wrap an LLM in a real-time audio layer then you know what I'm talking about.

That's where FastRTC comes in! It makes WebRTC and Websocket streams super easy with minimal code and overhead.

Check out our org: hf.co/fastrtc