42 235 230

Aymeric Roucher

m-ric

http://aymeric-roucher.github.io

AI & ML interests

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

Articles

Organizations

m-ric's activity

upvoted 3 papers 3 days ago

Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws

Paper • 2401.00448 • Published Dec 31, 2023 • 28

Scaling Autoregressive Models for Content-Rich Text-to-Image Generation

Paper • 2206.10789 • Published Jun 22, 2022 • 4

How Do Large Language Models Acquire Factual Knowledge During Pretraining?

Paper • 2406.11813 • Published Jun 17 • 30

upvoted 2 articles 7 days ago

Article

Welcome, Gradio 5

9 days ago

• 56

Article

Inference Endpoints Changelog 🚀

•

7 days ago

• 12

upvoted 2 papers 7 days ago

Falcon Mamba: The First Competitive Attention-free 7B Language Model

Paper • 2410.05355 • Published 11 days ago • 26

MLE-bench: Evaluating Machine Learning Agents on Machine Learning Engineering

Paper • 2410.07095 • Published 9 days ago • 6

upvoted a paper 8 days ago

Aria: An Open Multimodal Native Mixture-of-Experts Model

Paper • 2410.05993 • Published 10 days ago • 102

upvoted an article 9 days ago

Article

Faster Assisted Generation with Dynamic Speculation

10 days ago

• 25

upvoted 2 papers 10 days ago

Differential Transformer

Paper • 2410.05258 • Published 11 days ago • 152

Addition is All You Need for Energy-efficient Language Models

Paper • 2410.00907 • Published 17 days ago • 131

upvoted an article 14 days ago

Article

wHy DoNt YoU jUsT uSe ThE lLaMa ToKeNiZeR??

•

21 days ago

• 33

upvoted a paper 14 days ago

Were RNNs All We Needed?

Paper • 2410.01201 • Published 16 days ago • 42

upvoted an article 16 days ago

Article

RAG chatbot using llama3

•

Jul 7

• 73

upvoted a paper 17 days ago

Emu3: Next-Token Prediction is All You Need

Paper • 2409.18869 • Published 21 days ago • 83

upvoted an article 17 days ago

Article

A Short Summary of Chinese AI Global Expansion

•

17 days ago

• 12

upvoted a paper 21 days ago

AttnLRP: Attention-Aware Layer-wise Relevance Propagation for Transformers

Paper • 2402.05602 • Published Feb 8 • 4

upvoted a paper 22 days ago

Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Multimodal Models

Paper • 2409.17146 • Published 23 days ago • 96

upvoted a paper 23 days ago

FourCastNet: A Global Data-driven High-resolution Weather Model using Adaptive Fourier Neural Operators

Paper • 2202.11214 • Published Feb 22, 2022 • 1

upvoted 3 papers 24 days ago

LLMs Still Can't Plan; Can LRMs? A Preliminary Evaluation of OpenAI's o1 on PlanBench

Paper • 2409.13373 • Published 28 days ago • 2

PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change

Paper • 2206.10498 • Published Jun 21, 2022 • 1

YesBut: A High-Quality Annotated Multimodal Dataset for evaluating Satire Comprehension capability of Vision-Language Models

Paper • 2409.13592 • Published 28 days ago • 46

upvoted an article 24 days ago

Article

Does Daily Software Engineering Work Need Reasoning Models?

•

24 days ago

• 5

upvoted an article 25 days ago

Article

Exploring the Daily Papers Page on Hugging Face

25 days ago

• 31

upvoted a collection 29 days ago

Qwen2.5

Collection

Qwen2.5 language models, including pretrained and instruction-tuned models of 7 sizes, including 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B. • 45 items • Updated 30 days ago • 258

upvoted 2 articles 30 days ago

Article

Fine-tuning LLMs to 1.58bit: extreme quantization made easy

about 1 month ago

• 156

Article

Accelerate 1.0.0

Sep 13

• 48

upvoted 2 papers about 1 month ago

Chain of Thought Empowers Transformers to Solve Inherently Serial Problems

Paper • 2402.12875 • Published Feb 20 • 13

DSBench: How Far Are Data Science Agents to Becoming Data Science Experts?

Paper • 2409.07703 • Published Sep 12 • 66

upvoted 2 articles about 1 month ago

Article

Fine-tuning Parler TTS on a Specific Language

•

Sep 16

• 21

Article

Introducing Community Tools on HuggingChat

Sep 16

• 28

upvoted a paper about 1 month ago

Theory, Analysis, and Best Practices for Sigmoid Self-Attention

Paper • 2409.04431 • Published Sep 6 • 1

upvoted an article about 1 month ago

Article

Tool Use, Unified

Aug 12

• 56

upvoted 5 papers about 1 month ago

General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

Paper • 2409.01704 • Published Sep 3 • 80

NATURAL PLAN: Benchmarking LLMs on Natural Language Planning

Paper • 2406.04520 • Published Jun 6 • 10

Towards a Unified View of Preference Learning for Large Language Models: A Survey

Paper • 2409.02795 • Published Sep 4 • 72

Fire-Flyer AI-HPC: A Cost-Effective Software-Hardware Co-Design for Deep Learning

Paper • 2408.14158 • Published Aug 26 • 2

OLMoE: Open Mixture-of-Experts Language Models

Paper • 2409.02060 • Published Sep 3 • 77

upvoted an article about 1 month ago

Article

LAVE: Zero-shot VQA Evaluation on Docmatix with LLMs - Do We Still Need Fine-Tuning?

Jul 25

• 18

upvoted 2 papers about 1 month ago

Human Feedback is not Gold Standard

Paper • 2309.16349 • Published Sep 28, 2023 • 5

Prompt Chaining or Stepwise Prompt? Refinement in Text Summarization

Paper • 2406.00507 • Published Jun 1 • 1

upvoted a paper about 2 months ago

Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Models

Paper • 2408.02442 • Published Aug 5 • 18

upvoted an article about 2 months ago

Article

Scaling robotics datasets with video encoding

Aug 27

• 33

upvoted 5 papers about 2 months ago

Online DPO: Online Direct Preference Optimization with Fast-Slow Chasing

Paper • 2406.05534 • Published Jun 8 • 3

The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery

Paper • 2408.06292 • Published Aug 12 • 115

Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding

Paper • 2401.04398 • Published Jan 9 • 20

Diffusion Models Are Real-Time Game Engines

Paper • 2408.14837 • Published Aug 27 • 121

Building and better understanding vision-language models: insights and future directions

Paper • 2408.12637 • Published Aug 22 • 115

upvoted an article about 2 months ago

Article

Serverless Inference with Hugging Face and NVIDIA NIMs

Jul 29

• 26

upvoted a collection about 2 months ago

Jamba-1.5

Collection

The AI21 Jamba family of models are state-of-the-art, hybrid SSM-Transformer instruction following foundation models • 2 items • Updated Aug 22 • 80

upvoted an article about 2 months ago

Article

The 5 Most Under-Rated Tools on Hugging Face

Aug 22

• 84

upvoted a paper about 2 months ago

Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters

Paper • 2408.03314 • Published Aug 6 • 33

upvoted a paper 2 months ago

LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs

Paper • 2408.07055 • Published Aug 13 • 65

upvoted 2 articles 2 months ago

Article

Introduction to ggml

Aug 13

• 107

Article

XetHub is joining Hugging Face!

Aug 8

• 78

upvoted a paper 2 months ago

Sibyl: Simple yet Effective Agent Framework for Complex Real-world Reasoning

Paper • 2407.10718 • Published Jul 15 • 17

upvoted 3 papers 3 months ago

SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain

Paper • 2407.19584 • Published Jul 28 • 60

The Llama 3 Herd of Models

Paper • 2407.21783 • Published Jul 31 • 103

Towards Efficient Generative Large Language Model Serving: A Survey from Algorithms to Systems

Paper • 2312.15234 • Published Dec 23, 2023 • 3

upvoted an article 3 months ago

Article

Llama 3.1 - 405B, 70B & 8B with multilinguality and long context

Jul 23

• 203

Aymeric Roucher

AI & ML interests

Articles

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

Welcome, Gradio 5

Inference Endpoints Changelog 🚀

Faster Assisted Generation with Dynamic Speculation

wHy DoNt YoU jUsT uSe ThE lLaMa ToKeNiZeR??

RAG chatbot using llama3

A Short Summary of Chinese AI Global Expansion

Does Daily Software Engineering Work Need Reasoning Models?

Exploring the Daily Papers Page on Hugging Face

Fine-tuning LLMs to 1.58bit: extreme quantization made easy

Accelerate 1.0.0

Fine-tuning Parler TTS on a Specific Language

Introducing Community Tools on HuggingChat

Tool Use, Unified

LAVE: Zero-shot VQA Evaluation on Docmatix with LLMs - Do We Still Need Fine-Tuning?

Scaling robotics datasets with video encoding

Serverless Inference with Hugging Face and NVIDIA NIMs

The 5 Most Under-Rated Tools on Hugging Face

Introduction to ggml

XetHub is joining Hugging Face!

Llama 3.1 - 405B, 70B & 8B with multilinguality and long context