16 96 123

Aurélien-Morgan CLAUDON

Aurelien-Morgan

https://huggingface.co/retrain-pipelines

AI & ML interests

None yet

Recent Activity

reacted to jsulz's post with 🧠 1 day ago

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

upvoted a paper 1 day ago

SmolVLM: Redefining small and efficient multimodal models

new activity 4 days ago

blog-explorers/README:Preview dark/light toggle

View all activity

Organizations

Aurelien-Morgan's activity

upvoted a paper 1 day ago

SmolVLM: Redefining small and efficient multimodal models

Paper • 2504.05299 • Published 2 days ago • 129

upvoted an article 6 days ago

Article

The New and Fresh analytics in Inference Endpoints

20 days ago

• 19

upvoted an article 17 days ago

Article

NVIDIA's GTC 2025 Announcement for Physical AI Developers: New Open Models and Datasets

23 days ago

• 33

upvoted an article 19 days ago

Article

Xet is on the Hub

23 days ago

• 45

upvoted a paper 26 days ago

Transformers without Normalization

Paper • 2503.10622 • Published 27 days ago • 155

upvoted a paper about 1 month ago

nGPT: Normalized Transformer with Representation Learning on the Hypersphere

Paper • 2410.01131 • Published Oct 1, 2024 • 10

upvoted 2 articles about 1 month ago

Article

Trace & Evaluate your Agent with Arize Phoenix

Feb 28

• 37

Article

FastRTC: The Real-Time Communication Library for Python

Feb 25

• 152

upvoted 2 papers about 2 months ago

Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention

Paper • 2502.11089 • Published Feb 16 • 151

Qwen2.5-VL Technical Report

Paper • 2502.13923 • Published Feb 19 • 180

upvoted an article about 2 months ago

Article

π0 and π0-FAST: Vision-Language-Action Models for General Robot Control

Feb 4

• 138

upvoted a paper about 2 months ago

From LLMs to Actions: Latent Codes as Bridges in Hierarchical Robot Control

Paper • 2405.04798 • Published May 8, 2024 • 1

upvoted an article about 2 months ago

Article

SmolVLM2: Bringing Video Understanding to Every Device

Feb 20

• 226

upvoted a paper about 2 months ago

CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction

Paper • 2502.07316 • Published Feb 11 • 48

upvoted 2 articles about 2 months ago

Article

Introducing multi-backends (TRT-LLM, vLLM) support for Text Generation Inference

Jan 16

• 71

Article

Getting started with Hugging Face Inference Endpoints

Oct 14, 2022

• 1