Ross Wightman's picture

Ross Wightman

rwightman

·

AI & ML interests

Computer vision, transfer learning, semi/self supervised learning, robotics.

Recent Activity

upvoted an article about 12 hours ago

MiniMax-01 is Now Open-Source: Scaling Lightning Attention for the AI Agent Era

posted an update about 15 hours ago

I re-worked the JuptyerLab Space template recently. It's optimized for `timm` use, but will work great with `transformers` and other libs. Updated the base image, Python 3.12, Pillow-SIMD before better CPU use with image preprocessing, and made a number of other tweaks. From the Jupyter launcher you can run the terminal and setup a `timm` environment in moments with `setup_timm_dev` or `setup_timm_scripts` helpers. Give it a try, https://huggingface.co/spaces/timm/jupyterlab-timm

updated a model 1 day ago

timm/ese_vovnet57b.ra4_e3600_r256_in1k

View all activity

Articles

Timm ❤️ Transformers: Use any timm model with transformers

Trick or ResNet Treat

Mamba Out

Tiny Test Models

Searching for better (Full) ImageNet ViT Baselines

MobileNet Baselines

MobileNet-V4 (now in timm)

Organizations

rwightman's activity

upvoted an article about 12 hours ago

Article

MiniMax-01 is Now Open-Source: Scaling Lightning Attention for the AI Agent Era

By

•

3 days ago

• 32

upvoted an article 1 day ago

Article

Timm ❤️ Transformers: Use any timm model with transformers

2 days ago

• 25

upvoted a paper 29 days ago

Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference

Paper • 2412.13663 • Published Dec 18, 2024 • 123

upvoted 2 papers about 1 month ago

Phi-4 Technical Report

Paper • 2412.08905 • Published Dec 12, 2024 • 103

PaliGemma 2: A Family of Versatile VLMs for Transfer

Paper • 2412.03555 • Published Dec 4, 2024 • 124

upvoted a collection about 1 month ago

Common Models

The first generation of models pretrained on Common Corpus. • 5 items • Updated Dec 5, 2024 • 28

upvoted 2 papers about 2 months ago

MARS: Unleashing the Power of Variance Reduction for Training Large Models

Paper • 2411.10438 • Published Nov 15, 2024 • 13

Cautious Optimizers: Improving Training with One Line of Code

Paper • 2411.16085 • Published Nov 25, 2024 • 15

upvoted an article about 2 months ago

Article

🤗 Serve any model with Inference Endpoints + Custom Handlers

By

•

Nov 22, 2024

• 3

upvoted 2 collections 4 months ago

RDNet

DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTs [ECCV 2024] • 9 items • Updated Oct 16, 2024 • 3

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, 2024 • 5

upvoted 2 articles 6 months ago

Article

MobileNet Baselines

By

•

Jul 26, 2024

• 23

Article

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

Jul 25, 2024

• 18

upvoted a collection 6 months ago

🍃 MINT-1T

Data for "MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens" • 13 items • Updated Jul 24, 2024 • 58

upvoted 2 papers 6 months ago

PaliGemma: A versatile 3B VLM for transfer

Paper • 2407.07726 • Published Jul 10, 2024 • 68

Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs

Paper • 2406.16860 • Published Jun 24, 2024 • 60

upvoted a collection 6 months ago

Cambrian Data

3 items • Updated Jun 25, 2024 • 10

upvoted a paper 7 months ago

An Image is Worth 32 Tokens for Reconstruction and Generation

Paper • 2406.07550 • Published Jun 11, 2024 • 57

upvoted 2 collections 7 months ago

MobileCLIP Models + DataCompDR Data

MobileCLIP: Mobile-friendly image-text models with SOTA zero-shot capabilities. DataCompDR: Improved datasets for training image-text SOTA models. • 22 items • Updated Oct 4, 2024 • 26

MobileNetV4 pretrained weights

Weights for MobileNet-V4 pretrained in timm • 17 items • Updated Sep 22, 2024 • 18