29 159 150

Aymeric Roucher

m-ric

http://a-roucher.github.io

AymericRoucher

aymeric-roucher

AI & ML interests

MLE at Hugging Face 🤗 LLMs, Agents, RAG, Multimodal.

Articles

Organizations

m-ric's activity

upvoted an article 3 days ago

Article

Welcome Gemma 2 - Google's new open LLM

4 days ago

• 64

upvoted 2 articles 4 days ago

Article

Fine-tuning Florence-2 - Microsoft's Cutting-edge Vision Language Models

7 days ago

• 112

Article

XLSCOUT Unveils ParaEmbed 2.0: a Powerful Embedding Model Tailored for Patents and IP with Expert Support from Hugging Face

6 days ago

• 8

upvoted an article 6 days ago

Article

Faster fine-tuning using TRL & Unsloth

Jan 10

• 26

upvoted an article 7 days ago

Article

Build Agentic Workflow using OpenAGI and HuggingFace models

•

5 days ago

• 5

upvoted a paper 13 days ago

Hallucination-Free? Assessing the Reliability of Leading AI Legal Research Tools

Paper • 2405.20362 • Published May 30 • 2

upvoted a paper 16 days ago

DataComp: In search of the next generation of multimodal datasets

Paper • 2304.14108 • Published Apr 27, 2023 • 2

upvoted a paper 18 days ago

Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation

Paper • 2406.06525 • Published 20 days ago • 60

upvoted 2 papers 21 days ago

An Introduction to Vision-Language Modeling

Paper • 2405.17247 • Published May 27 • 77

MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark

Paper • 2406.01574 • Published 27 days ago • 42

upvoted an article 23 days ago

Article

Making sense of this mess

24 days ago

• 14

upvoted an article 24 days ago

Article

Extracting Concepts from LLMs: Anthropic’s recent discoveries 📖

•

11 days ago

• 25

upvoted a paper 24 days ago

Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Paper • 2401.05566 • Published Jan 10 • 24

upvoted 2 articles 28 days ago

Article

How Sempre Health is leveraging the Expert Acceleration Program to accelerate their ML roadmap

May 19, 2022

• 1

Article

Space secrets security update

May 31

• 50

upvoted an article about 1 month ago

Article

Benchmarking Text Generation Inference

May 29

• 24

upvoted 6 papers about 1 month ago

LoRA Learns Less and Forgets Less

Paper • 2405.09673 • Published May 15 • 80

Metacognitive Prompting Improves Understanding in Large Language Models

Paper • 2308.05342 • Published Aug 10, 2023 • 2

Language Models are Few-Shot Learners

Paper • 2005.14165 • Published May 28, 2020 • 10

Large Language Models Struggle to Learn Long-Tail Knowledge

Paper • 2211.08411 • Published Nov 15, 2022 • 3

Executable Code Actions Elicit Better LLM Agents

Paper • 2402.01030 • Published Feb 1 • 22

Your Transformer is Secretly Linear

Paper • 2405.12250 • Published May 19 • 143

upvoted 3 articles about 1 month ago

Article

AI has a problem with objectifying women

•

May 24

• 54

Article

Let's talk about LLM evaluation

•

May 23

• 92

Article

Introducing Spaces Dev Mode for a seamless developer experience

May 21

• 12

upvoted a paper about 1 month ago

Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy

Paper • 2305.15294 • Published May 24, 2023 • 1

upvoted an article about 1 month ago

Article

PaliGemma – Google's Cutting-Edge Open Vision Language Model

May 14

• 156

upvoted a paper about 2 months ago

MambaOut: Do We Really Need Mamba for Vision?

Paper • 2405.07992 • Published May 13 • 1

upvoted an article about 2 months ago

Article

2024-04-22 - Hub Incident Post Mortem

•

May 17

• 17

upvoted a paper about 2 months ago

No Language Left Behind: Scaling Human-Centered Machine Translation

Paper • 2207.04672 • Published Jul 11, 2022 • 1

upvoted 2 articles about 2 months ago

Article

Hugging Face x LangChain : A new partner package in LangChain

May 14

• 83

Article

Energy Star Ratings for AI Models

•

May 9

• 19

upvoted a paper about 2 months ago

Data Interpreter: An LLM Agent For Data Science

Paper • 2402.18679 • Published Feb 28 • 1

upvoted 3 articles about 2 months ago

Article

Powerful ASR + diarization + speculative decoding with Hugging Face Inference Endpoints

May 1

• 58

Article

Subscribe to Enterprise Hub with your AWS Account

May 9

• 6

Article

License to Call: Introducing Transformers Agents 2.0

May 13

• 98

upvoted 2 papers about 2 months ago

HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering

Paper • 1809.09600 • Published Sep 25, 2018 • 2

Training Verifiers to Solve Math Word Problems

Paper • 2110.14168 • Published Oct 27, 2021 • 4

upvoted an article about 2 months ago

Article

Vision Language Models Explained

Apr 11

• 113

upvoted 4 papers about 2 months ago

What matters when building vision-language models?

Paper • 2405.02246 • Published May 3 • 91

Fast Inference from Transformers via Speculative Decoding

Paper • 2211.17192 • Published Nov 30, 2022 • 3

Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

Paper • 2401.10774 • Published Jan 19 • 50

Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding

Paper • 2402.12374 • Published Feb 19 • 3

upvoted an article 2 months ago

Article

Improving Prompt Consistency with Structured Generations

Apr 30

• 48

upvoted 4 papers 2 months ago

Dynamic Typography: Bringing Words to Life

Paper • 2404.11614 • Published Apr 17 • 40

Chinchilla Scaling: A replication attempt

Paper • 2404.10102 • Published Apr 15 • 1

Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone

Paper • 2404.14219 • Published Apr 22 • 240

AutoCrawler: A Progressive Understanding Web Agent for Web Crawler Generation

Paper • 2404.12753 • Published Apr 19 • 39

upvoted an article 2 months ago

Article

Introducing the Open Chain of Thought Leaderboard

Apr 23

• 22

upvoted a paper 2 months ago

Training-Free Long-Context Scaling of Large Language Models

Paper • 2402.17463 • Published Feb 27 • 19

upvoted 3 articles 2 months ago

Article

Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent

Apr 22

• 75

Article

Synthetic data: save money, time and carbon with open source

Feb 16

• 32

Article

Welcome Llama 3 - Meta's new open LLM

Apr 18

• 253

upvoted 2 collections 2 months ago

Meta Llama 3

Collection

This collection hosts the transformers and original repos of the Meta Llama 3 and Llama Guard 2 releases • 5 items • Updated Apr 18 • 614

fuck quadratic attention

Collection

11 items • Updated Apr 24 • 20

upvoted a paper 2 months ago

Hydragen: High-Throughput LLM Inference with Shared Prefixes

Paper • 2402.05099 • Published Feb 7 • 17

upvoted an article 3 months ago

Article

Introducing Idefics2: A Powerful 8B Vision-Language Model for the community

Apr 15

• 144

upvoted 2 papers 3 months ago

LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale

Paper • 2208.07339 • Published Aug 15, 2022 • 4

GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers

Paper • 2210.17323 • Published Oct 31, 2022 • 6

upvoted an article 3 months ago

Article

It's raining diffusion personalization techniques☔️🎭🖼️

•

Apr 11

• 16

Aymeric Roucher

AI & ML interests

Articles

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

Welcome Gemma 2 - Google's new open LLM

Fine-tuning Florence-2 - Microsoft's Cutting-edge Vision Language Models

XLSCOUT Unveils ParaEmbed 2.0: a Powerful Embedding Model Tailored for Patents and IP with Expert Support from Hugging Face

Faster fine-tuning using TRL & Unsloth

Build Agentic Workflow using OpenAGI and HuggingFace models

Making sense of this mess

Extracting Concepts from LLMs: Anthropic’s recent discoveries 📖

How Sempre Health is leveraging the Expert Acceleration Program to accelerate their ML roadmap

Space secrets security update

Benchmarking Text Generation Inference

AI has a problem with objectifying women

Let's talk about LLM evaluation

Introducing Spaces Dev Mode for a seamless developer experience

PaliGemma – Google's Cutting-Edge Open Vision Language Model

2024-04-22 - Hub Incident Post Mortem

Hugging Face x LangChain : A new partner package in LangChain

Energy Star Ratings for AI Models

Powerful ASR + diarization + speculative decoding with Hugging Face Inference Endpoints

Subscribe to Enterprise Hub with your AWS Account

License to Call: Introducing Transformers Agents 2.0

Vision Language Models Explained

Improving Prompt Consistency with Structured Generations

Introducing the Open Chain of Thought Leaderboard

Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent

Synthetic data: save money, time and carbon with open source

Welcome Llama 3 - Meta's new open LLM

Introducing Idefics2: A Powerful 8B Vision-Language Model for the community

It's raining diffusion personalization techniques☔️🎭🖼️