18 102 130

Aurélien-Morgan CLAUDON

Aurelien-Morgan

https://huggingface.co/retrain-pipelines

AI & ML interests

None yet

Recent Activity

posted an update about 22 hours ago

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

upvoted a paper about 22 hours ago

Insights into DeepSeek-V3: Scaling Challenges and Reflections on Hardware for AI Architectures

liked a Space 1 day ago

huggingface/space-build

View all activity

Organizations

Aurelien-Morgan's activity

posted an update about 22 hours ago

Post

250

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

upvoted a paper about 22 hours ago

Insights into DeepSeek-V3: Scaling Challenges and Reflections on Hardware for AI Architectures

Paper • 2505.09343 • Published 2 days ago • 39

liked a Space 1 day ago

Space Build

🐨

Generate static files for spaces

commented on LeRobot Community Datasets: The “ImageNet” of Robotics — When and How? 5 days ago

Lots of insights and wisdom. Very nice. Articulating these ideas and notions has much value and will pay off. Thank you.

upvoted an article 5 days ago

Article

LeRobot Community Datasets: The “ImageNet” of Robotics — When and How?

and 6 others •

6 days ago

• 45

liked a Space 7 days ago

340

DreamO

🐨

A Unified Framework for Image Customization

liked a Space 8 days ago

WikiRacing Language Models

🏃

Find answers by racing against LLM in a quiz game

published an article 8 days ago

Article

retrain-pipelines and the almighty function-caller

•

18 days ago

• 5

upvoted a paper 9 days ago

A Survey on Inference Engines for Large Language Models: Perspectives on Optimization and Efficiency

Paper • 2505.01658 • Published 14 days ago • 31

liked a Space 12 days ago

Pytorch Day Prez

🔥

View a presentation on PyTorch and Transformers integration

liked a model 14 days ago

unsloth/Qwen3-1.7B-Base

Text Generation • Updated 4 days ago • 872 • 1

posted an update 18 days ago

Post

3129

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 🔥 19 days ago

Post

5758

🦥 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 19 days ago

Post

661

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.