youssef boulaouane's picture

youssef boulaouane

byoussef

·

Boulaouaney

AI & ML interests

None yet

Recent Activity

Reacted to rwightman's post with 🚀 4 days ago

Want to validate some hparams or figure out what `timm` model to use before commiting to download or training with a large dataset? Try mini-imagenet: https://huggingface.co/datasets/timm/mini-imagenet I had this sitting on my drive and forgot where I pulled it together from. It's 100 classes of imagenet, 50k train and 10k val images (from ImageNet-1k train set), and 5k test images (from ImageNet-1k val set). 7.4GB instead of > 100GB for the full ImageNet-1k. This ver is not reduced resolution like some other 'mini' versions. Super easy to use with timm train/val scripts, checkout the dataset card. I often check fine-tuning with even smaller datasets like: * https://huggingface.co/datasets/timm/resisc45 * https://huggingface.co/datasets/timm/oxford-iiit-pet But those are a bit small to train any modest size model w/o starting from pretrained weights.

upvoted a collection 10 days ago

Nov 15 Releases 🍂

upvoted a collection 14 days ago

View all activity

Organizations

byoussef's activity

upvoted a collection 10 days ago

Nov 15 Releases 🍂

15 items • Updated 10 days ago • 6

upvoted a collection 14 days ago

OpenCoder

OpenCoder is an open and reproducible code LLM family which matches the performance of top-tier code LLMs. • 8 items • Updated 1 day ago • 73

upvoted a collection about 1 month ago

timm tiny test models

A collection of very small (~300-500k parameter) models at 160x160 resolution, for testing purposes. Trained on ImageNet-1k. • 13 items • Updated Oct 2 • 3

upvoted an article about 1 month ago

Article

Welcome, Gradio 5

Oct 9

• 72

upvoted an article about 2 months ago

Article

Tiny Test Models

By

•

Oct 2

• 6

upvoted a paper about 2 months ago

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second

Paper • 2410.02073 • Published Oct 2 • 40

upvoted a paper 3 months ago

Diffusion Models Are Real-Time Game Engines

Paper • 2408.14837 • Published Aug 27 • 121

upvoted a collection 3 months ago

💻 Local SmolLMs

SmolLM models in MLC, ONNX and GGUF format for local applications + in-browser demos • 14 items • Updated Aug 20 • 46

upvoted an article 4 months ago

Article

MobileNet Baselines

By

•

Jul 26

• 23

upvoted a paper 4 months ago

BetterDepth: Plug-and-Play Diffusion Refiner for Zero-Shot Monocular Depth Estimation

Paper • 2407.17952 • Published Jul 25 • 29

upvoted a collection 4 months ago

🪐 SmolLM

A series of smol LLMs: 135M, 360M and 1.7B. We release base and Instruct models as well as the training corpus and some WebGPU demos • 12 items • Updated Aug 18 • 200

upvoted an article 5 months ago

Article

Image-based search engine

By

•

Jul 4

• 23

upvoted a paper 5 months ago

The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale

Paper • 2406.17557 • Published Jun 25 • 86

upvoted 4 collections 5 months ago

Florence

9 items • Updated Jul 11 • 160

MobileNetV4_Conv Pretrained TFLite Models

These TFLite models were converted from the pretrained Pytorch weights on timm. • 7 items • Updated Jun 19 • 2

DeepSeekCoder-V2

6 items • Updated Sep 5 • 83

MobileNetV4 pretrained weights

Weights for MobileNet-V4 pretrained in timm • 17 items • Updated Sep 22 • 17

upvoted an article 6 months ago

Article

Training an Object Detection Model with AutoTrain

By

•

Jun 5

• 14

upvoted a paper 6 months ago

On the Efficiency of Convolutional Neural Networks

Paper • 2404.03617 • Published Apr 4 • 4

upvoted an article 6 months ago

Article

MobileNet-V4 (now in timm)

By

•

Jun 17

• 39