EPFL Machine Learning and Optimization Laboratory

epfml's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Articles

vsabolcec 

in epfml/FineWeb-HQ 7 days ago

Error when loading LFS files

4

#2 opened about 1 month ago by

oligou

vsabolcec 

updated a collection 3 months ago

FineWeb-HQ datasets

Collection

Collection containing FineWeb-HQ and FineWeb2-HQ quality filtered datasets. • 3 items • Updated Oct 8

mjaggi 

authored a paper 3 months ago

Apertus: Democratizing Open and Compliant LLMs for Global Language Environments

Paper • 2509.14233 • Published Sep 17 • 14

NXz64Fdf8Y 

updated a dataset 3 months ago

epfml/FineWeb-HQ

Viewer • Updated Sep 30 • 2.45B • 25.9k • 4

Andron00e 

authored a paper 3 months ago

Apertus: Democratizing Open and Compliant LLMs for Global Language Environments

Paper • 2509.14233 • Published Sep 17 • 14

mjaggi 

authored a paper 4 months ago

Benchmarking Optimizers for Large Language Model Pretraining

Paper • 2509.01440 • Published Sep 1 • 24

MatPag 

authored a paper 4 months ago

Benchmarking Optimizers for Large Language Model Pretraining

Paper • 2509.01440 • Published Sep 1 • 24

Andron00e 

authored 2 papers 4 months ago

Gradient Clipping Improves AdaGrad when the Noise Is Heavy-Tailed

Paper • 2406.04443 • Published Jun 6, 2024

Benchmarking Optimizers for Large Language Model Pretraining

Paper • 2509.01440 • Published Sep 1 • 24

haeggee 

authored 2 papers 5 months ago

BaCaDI: Bayesian Causal Discovery with Unknown Interventions

Paper • 2206.01665 • Published Jun 3, 2022 • 2

Inverse Scaling in Test-Time Compute

Paper • 2507.14417 • Published Jul 19 • 27

NXz64Fdf8Y 

authored a paper 6 months ago

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

Paper • 2506.20920 • Published Jun 26 • 75

mjaggi 

authored a paper 6 months ago

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

Paper • 2506.20920 • Published Jun 26 • 75

vsabolcec 

authored a paper 6 months ago

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

Paper • 2506.20920 • Published Jun 26 • 75

loubnabnl 

authored a paper 7 months ago

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

Paper • 2506.05209 • Published Jun 5 • 59

loubnabnl 

posted an update 8 months ago

view post

Post

6070

SmolVLM is now available on PocketPal — you can run it offline on your smartphone to interpret the world around you. 🌍📱

And check out this real-time camera demo by @ngxson , powered by llama.cpp:
https://github.com/ngxson/smolvlm-realtime-webcam
https://x.com/pocketpal_ai

See translation

• 

• 
• 
• 
• 4 replies

·

❤️

11

11

😎

1

1

+

Reply

loubnabnl 

authored a paper 9 months ago

SmolVLM: Redefining small and efficient multimodal models

Paper • 2504.05299 • Published Apr 7 • 202

loubnabnl 

authored a paper 11 months ago

SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

Paper • 2502.02737 • Published Feb 4 • 252