32 211 201

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 a collection 3 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 4 days ago • 151

upvoted 2 articles 4 days ago

Article

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

5 days ago

• 113

Article

Accelerate 1.0.0

10 days ago

• 32

upvoted a paper 5 days ago

Chain of Thought Empowers Transformers to Solve Inherently Serial Problems

Paper • 2402.12875 • Published Feb 20 • 12

upvoted a paper 6 days ago

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

Paper • 2409.07703 • Published 11 days ago • 59

upvoted 2 articles 6 days ago

Article

Fine-tuning Parler TTS on a Specific Language

•

6 days ago

• 15

Article

Introducing Community Tools on HuggingChat

7 days ago

• 25

upvoted a paper 10 days ago

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

Paper • 2409.04431 • Published 16 days ago • 1

upvoted an article 11 days ago

Article

Tool Use, Unified

Aug 12

• 49

upvoted a paper 11 days ago

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

Paper • 2409.01704 • Published 19 days ago • 72

upvoted 2 papers 12 days ago

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 18 days ago • 70

upvoted 2 papers 18 days ago

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

Paper • 2408.14158 • Published 27 days ago • 2

OLMoE: Open Mixture-of-Experts Language Models

Paper • 2409.02060 • Published 19 days ago • 75

upvoted an article 19 days ago

Article

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

Jul 25

• 18

upvoted 2 papers 19 days 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 20 days 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 • 17

upvoted an article 23 days ago

Article

Scaling robotics datasets with video encoding

27 days ago

• 31

upvoted 3 papers 23 days ago

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

Paper • 2406.05534 • Published Jun 8 • 2

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

Paper • 2408.06292 • Published Aug 12 • 114

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

Paper • 2401.04398 • Published Jan 9 • 20

upvoted 2 papers 25 days ago

Diffusion Models Are Real-Time Game Engines

Paper • 2408.14837 • Published 26 days ago • 119

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

Paper • 2408.12637 • Published about 1 month ago • 109

upvoted an article about 1 month ago

Article

Serverless Inference with Hugging Face and NVIDIA NIMs

Jul 29

• 26

upvoted a collection about 1 month 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 • 72

upvoted an article about 1 month ago

Article

The 5 Most Under-Rated Tools on Hugging Face

Aug 22

• 76

upvoted 2 papers about 1 month ago

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

Paper • 2408.03314 • Published Aug 6 • 32

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

Paper • 2408.07055 • Published Aug 13 • 65

upvoted an article about 1 month ago

Article

Introduction to ggml

Aug 13

• 92

upvoted an article about 2 months ago

Article

XetHub is joining Hugging Face!

Aug 8

• 76

upvoted 3 papers about 2 months ago

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

Paper • 2407.10718 • Published Jul 15 • 17

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 • 102

upvoted a paper 2 months ago

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

Paper • 2312.15234 • Published Dec 23, 2023 • 3

upvoted an article 2 months ago

Article

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

Jul 23

• 195

upvoted a paper 2 months ago

GPTs are GPTs: An Early Look at the Labor Market Impact Potential of Large Language Models

Paper • 2303.10130 • Published Mar 17, 2023 • 3

upvoted an article 2 months ago

Article

The Rise of Agentic Data Generation

•

Jul 15

• 74

upvoted 4 papers 2 months ago

RouteLLM: Learning to Route LLMs with Preference Data

Paper • 2406.18665 • Published Jun 26 • 5

SWE-bench: Can Language Models Resolve Real-World GitHub Issues?

Paper • 2310.06770 • Published Oct 10, 2023 • 4

BERT Rediscovers the Classical NLP Pipeline

Paper • 1905.05950 • Published May 15, 2019 • 2

DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models

Paper • 2309.03883 • Published Sep 7, 2023 • 33

upvoted 3 articles 3 months ago

Article

Banque des Territoires (CDC Group) x Polyconseil x Hugging Face: Enhancing a Major French Environmental Program with a Sovereign Data Solution

Jul 9

• 4

Article

Google Cloud TPUs made available to Hugging Face users

Jul 9

• 19

Article

Announcing New Dataset Search Features

Jul 8

• 22

upvoted 5 papers 3 months ago

APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasets

Paper • 2406.18518 • Published Jun 26 • 23

Agentless: Demystifying LLM-based Software Engineering Agents

Paper • 2407.01489 • Published Jul 1 • 42

Precise Zero-Shot Dense Retrieval without Relevance Labels

Paper • 2212.10496 • Published Dec 20, 2022 • 2

Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection

Paper • 2310.11511 • Published Oct 17, 2023 • 74

LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs

Paper • 2406.15319 • Published Jun 21 • 60

upvoted an article 3 months ago

Article

Our Transformers Code Agent beats the GAIA benchmark!

Jul 1

• 44

upvoted a collection 3 months ago

The SPRIGHT T2I collection

Collection

This collection contains the datasets, model, paper, and demo associated with the SPRIGHT (SPatially RIGHT) release. • 5 items • Updated Apr 2 • 5

upvoted 6 articles 3 months ago

Article

Going multimodal: How Prezi is leveraging the Hub and the Expert Support Program to accelerate their ML roadmap

Jun 19

• 11

Article

Welcome Gemma 2 - Google's new open LLM

Jun 27

• 116

Article

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

Jun 24

• 166

Article

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

Jun 25

• 9

Article

Faster fine-tuning using TRL & Unsloth

Jan 10

• 35

Article

Build Agentic Workflow using OpenAGI and HuggingFace models

•

Jun 26

• 8

upvoted 2 papers 3 months ago

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

Paper • 2405.20362 • Published May 30 • 2

DataComp: In search of the next generation of multimodal datasets

Paper • 2304.14108 • Published Apr 27, 2023 • 2

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

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

The Rise of Agentic Data Generation

Banque des Territoires (CDC Group) x Polyconseil x Hugging Face: Enhancing a Major French Environmental Program with a Sovereign Data Solution

Google Cloud TPUs made available to Hugging Face users

Announcing New Dataset Search Features

Our Transformers Code Agent beats the GAIA benchmark!

Going multimodal: How Prezi is leveraging the Hub and the Expert Support Program to accelerate their ML roadmap

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