Pavel Iakubovskii's picture

Pavel Iakubovskii

qubvel-hf

·

AI & ML interests

Computer Vision models

Recent Activity

upvoted an article 3 days ago

1 Billion Classifications

upvoted a paper 3 days ago

Scaling Pre-training to One Hundred Billion Data for Vision Language Models

upvoted an article 4 days ago

From Chunks to Blocks: Accelerating Uploads and Downloads on the Hub

View all activity

Organizations

qubvel-hf's activity

upvoted an article 3 days ago

Article

1 Billion Classifications

4 days ago

• 34

upvoted a paper 3 days ago

Scaling Pre-training to One Hundred Billion Data for Vision Language Models

Paper • 2502.07617 • Published 5 days ago • 24

upvoted an article 4 days ago

Article

From Chunks to Blocks: Accelerating Uploads and Downloads on the Hub

5 days ago

• 42

upvoted an article 5 days ago

Article

From Llasa to Llasagna 🍕: Finetuning LLaSA to generates Italian speech and other languages

By

and 1 other •

5 days ago

• 21

upvoted a collection 9 days ago

DepthPro Models

Depth Pro: Sharp Monocular Metric Depth in Less Than a Second • 4 items • Updated 9 days ago • 7

upvoted an article 28 days ago

Article

Simplifying Alignment: From RLHF to Direct Preference Optimization (DPO)

By

•

28 days ago

• 13

upvoted an article 30 days ago

Article

Timm ❤️ Transformers: Use any timm model with transformers

Jan 16

• 39

upvoted 2 collections about 1 month ago

ViTPose

Collection for ViTPose models based on transformers implementation. • 10 items • Updated Jan 12 • 12

Segformer

Transformer-based semantic segmentation model by Nvidia • 15 items • Updated Jan 13 • 4

upvoted a paper about 2 months ago

TRecViT: A Recurrent Video Transformer

Paper • 2412.14294 • Published Dec 18, 2024 • 13

upvoted a collection about 2 months 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, 2024 • 5

upvoted an article 3 months ago

Article

ColPali: Efficient Document Retrieval with Vision Language Models 👀

By

•

Jul 5, 2024

• 200

upvoted a collection 3 months ago

Flow-Judge-v0.1

Flow-Judge-v0.1 models • 5 items • Updated Sep 17, 2024 • 19

upvoted a paper 4 months ago

Visual Instruction Tuning

Paper • 2304.08485 • Published Apr 17, 2023 • 13

upvoted an article 4 months ago

Article

Faster Assisted Generation with Dynamic Speculation

Oct 8, 2024

• 45

upvoted a collection 4 months ago

Humans

A Hub for Human-Centric 3D Vision • 4 items • Updated Oct 7, 2024 • 2

upvoted a paper 4 months ago

Multi-HMR: Multi-Person Whole-Body Human Mesh Recovery in a Single Shot

Paper • 2402.14654 • Published Feb 22, 2024 • 2

upvoted a collection 5 months ago

Llama 3.2

This collection hosts the transformers and original repos of the Llama 3.2 and Llama Guard 3 • 15 items • Updated Dec 6, 2024 • 569

upvoted a collection 6 months ago

Jamba-1.5

The AI21 Jamba family of models are state-of-the-art, hybrid SSM-Transformer instruction following foundation models • 2 items • Updated Aug 22, 2024 • 84

upvoted an article 6 months ago

Article

Introduction to ggml

Aug 13, 2024

• 147