Elie Bakouch's picture

Elie Bakouch

eliebak

·

AI & ML interests

Training LLM's @ 🤗

Recent Activity

commented on a paper 2 days ago

Fast and Simplex: 2-Simplicial Attention in Triton

upvoted a paper 2 days ago

Fast and Simplex: 2-Simplicial Attention in Triton

commented on a paper 2 days ago

Fast and Simplex: 2-Simplicial Attention in Triton

View all activity

Organizations

upvoted a paper 2 days ago

Fast and Simplex: 2-Simplicial Attention in Triton

Paper • 2507.02754 • Published 2 days ago • 15

upvoted a collection 6 days ago

ERNIE 4.5

collection of ERNIE 4.5 models. "-Paddle" models use PaddlePaddle weights, while "-PT" models use Transformer-style PyTorch weights. • 23 items • Updated 3 days ago • 139

upvoted a paper 9 days ago

FineWeb2: One Pipeline to Scale Them All -- Adapting Pre-Training Data Processing to Every Language

Paper • 2506.20920 • Published 10 days ago • 57

upvoted an article 13 days ago

Article

🤔👀🎬🖥️📖 Kimi-VL-A3B-Thinking-2506: A Quick Navigation

By

and 1 other •

14 days ago

• 55

upvoted 2 papers 18 days ago

Essential-Web v1.0: 24T tokens of organized web data

Paper • 2506.14111 • Published 19 days ago • 40

AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL Synergy

Paper • 2506.13284 • Published 20 days ago • 23

upvoted a changelog 20 days ago

Changelog

New Model Filtering Options on the Hub

20 days ago

• 63

upvoted a paper 22 days ago

Comment on The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity

Paper • 2506.09250 • Published 25 days ago • 28

upvoted a collection 25 days ago

MiniCPM4

MiniCPM4: Ultra-Efficient LLMs on End Devices • 22 items • Updated 14 days ago • 66

upvoted a paper 25 days ago

MiniCPM4: Ultra-Efficient LLMs on End Devices

Paper • 2506.07900 • Published 26 days ago • 81

upvoted an article 27 days ago

Article

Inside the family of Smol models

By

and 1 other •

Feb 27

• 12

upvoted an article 29 days ago

Article

The Common Pile v0.1

By

and 2 others •

30 days ago

• 43

upvoted a paper 29 days ago

The Common Pile v0.1: An 8TB Dataset of Public Domain and Openly Licensed Text

Paper • 2506.05209 • Published about 1 month ago • 42

upvoted a collection 30 days ago

Common Pile v0.1

All resources related to Common Pile v0.1, an 8TB dataset of public domain and openly licensed text • 4 items • Updated 30 days ago • 26

upvoted an article about 1 month ago

Article

FineWeb2-C: Help Build Better Language Models in Your Language

By

and 5 others •

Dec 23, 2024

• 20

upvoted 2 collections about 1 month ago

👩‍💻 OlympicCoder

Reasoning datasets and models for competitive coding • 4 items • Updated May 13 • 19

🧠 Reasoning datasets

Datasets with reasoning traces for math and code released by the community • 24 items • Updated May 19 • 154

upvoted an article about 1 month ago

Article

Interactive Tools for machine learning, deep learning, and math

By

•

May 26

• 44

upvoted a paper about 2 months ago

Qwen3 Technical Report

Paper • 2505.09388 • Published May 14 • 209

upvoted an article about 2 months ago

Article

The Transformers Library: standardizing model definitions

By

and 3 others •

May 15

• 115