Aymeric Roucher's picture

Aymeric Roucher

m-ric

·

http://aymeric-roucher.github.io

AI & ML interests

Leading Agents at Hugging Face 🤗

Recent Activity

liked a Space 3 days ago

data-agents/jupyter-agent

posted an update 3 days ago

After 6 years, BERT, the workhorse of encoder models, finally gets a replacement: 𝗪𝗲𝗹𝗰𝗼𝗺𝗲 𝗠𝗼𝗱𝗲𝗿𝗻𝗕𝗘𝗥𝗧! 🤗 We talk a lot about ✨Generative AI✨, meaning "Decoder version of the Transformers architecture", but this is only one of the ways to build LLMs: encoder models, that turn a sentence in a vector, are maybe even more widely used in industry than generative models. The workhorse for this category has been BERT since its release in 2018 (that's prehistory for LLMs). It's not a fancy 100B parameters supermodel (just a few hundred millions), but it's an excellent workhorse, kind of a Honda Civic for LLMs. Many applications use BERT-family models - the top models in this category cumulate millions of downloads on the Hub. ➡️ Now a collaboration between Answer.AI and LightOn just introduced BERT's replacement: ModernBERT. 𝗧𝗟;𝗗𝗥: 🏛️ Architecture changes: ⇒ First, standard modernizations: - Rotary positional embeddings (RoPE) - Replace GeLU with GeGLU, - Use Flash Attention 2 ✨ The team also introduced innovative techniques like alternating attention instead of full attention, and sequence packing to get rid of padding overhead. 🥇 As a result, the model tops the game of encoder models: It beats previous standard DeBERTaV3 for 1/5th the memory footprint, and runs 4x faster! Read the blog post 👉 https://huggingface.co/blog/modernbert

updated a Space 3 days ago

m-ric/ai-travel-planner

View all activity

Articles

Expert Support case study: Bolstering a RAG app with LLM-as-a-Judge

Our Transformers Code Agent beats the GAIA benchmark!

Extracting Concepts from LLMs: Anthropic’s recent discoveries 📖

License to Call: Introducing Transformers Agents 2.0

Open-source LLMs as LangChain Agents

Organizations

m-ric's activity

upvoted an article 6 days ago

Article

🇪🇺✍️ EU AI Act: Systemic Risks in the First CoP Draft Comments ✍️🇪🇺

By

•

10 days ago

• 11

upvoted a collection 6 days ago

Diffusion Tools

4 items • Updated Apr 30 • 5

upvoted a collection 7 days ago

GUI agents

A collection of papers on GUI agents • 3 items • Updated 8 days ago • 5

upvoted a paper 8 days ago

AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials

Paper • 2412.09605 • Published 10 days ago • 25

upvoted 2 papers 12 days ago

If LLM Is the Wizard, Then Code Is the Wand: A Survey on How Code Empowers Large Language Models to Serve as Intelligent Agents

Paper • 2401.00812 • Published Jan 1 • 3

Code Agents are State of the Art Software Testers

Paper • 2406.12952 • Published Jun 18 • 1

upvoted a collection 12 days ago

Awesome Computer Use Agents

https://github.com/ranpox/awesome-computer-use • 25 items • Updated 4 days ago • 3

upvoted a paper 12 days ago

Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction

Paper • 2412.04454 • Published 17 days ago • 46

upvoted 2 articles 17 days ago

Article

🐺🐦‍⬛ LLM Comparison/Test: 25 SOTA LLMs (including QwQ) through 59 MMLU-Pro CS benchmark runs

By

•

18 days ago

• 70

Article

They Said It Couldn’t Be Done

By

•

17 days ago

• 73

upvoted 2 papers 18 days ago

Agent Workflow Memory

Paper • 2409.07429 • Published Sep 11 • 28

ShowUI: One Vision-Language-Action Model for GUI Visual Agent

Paper • 2411.17465 • Published 26 days ago • 76

upvoted an article 19 days ago

Article

EuroLLM-9B

By

•

20 days ago

• 103

upvoted a paper 20 days ago

DynaSaur: Large Language Agents Beyond Predefined Actions

Paper • 2411.01747 • Published Nov 4 • 16

upvoted 3 articles about 1 month ago

Article

Introducing Observers: AI Observability with Hugging Face datasets through a lightweight SDK

By

•

Nov 21

• 34

Article

Halo: Open Source Health Tracking with Wearables

By

•

Nov 19

• 95

Article

Decoding Strategies in Large Language Models

By

•

Oct 29

• 38

upvoted 3 papers about 1 month ago

Watermark Anything with Localized Messages

Paper • 2411.07231 • Published Nov 11 • 20

HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems

Paper • 2411.02959 • Published Nov 5 • 64

OpenCoder: The Open Cookbook for Top-Tier Code Large Language Models

Paper • 2411.04905 • Published Nov 7 • 111