A-vision models based on Qwen visual language models
AI & ML interests
Scientific research; Natural language processing; A family of LLMs; Computer vision.
Recent Activity
View all activity
Organization Card
We build advanced AI solutions to improve search, communication, and content understanding across our platform. We develop and train our own Large Language Models (LLMs) to power smarter user experiences - and now we’re excited to share some of them with the open-source community! 🚀
Explore, experiment, and collaborate with us to make our models even better 💙
models
10
AvitoTech/DINO-v2-small-for-animal-identification
Image Feature Extraction
•
Updated
•
40
•
1
AvitoTech/SigLIP-Base-for-animal-identification
Image Feature Extraction
•
Updated
•
33
•
1
AvitoTech/SigLIP2-Base-for-animal-identification
Image Feature Extraction
•
Updated
•
26
•
1
AvitoTech/SigLIP2-giant
Image Feature Extraction
•
Updated
•
42
•
4
AvitoTech/SigLIP2-giant-e5small-v2-gating
Feature Extraction
•
Updated
•
16
•
1
AvitoTech/CLIP-ViT-base-for-animal-identification
Image Feature Extraction
•
Updated
•
24
AvitoTech/Zer0int-CLIP-L-for-animal-identification
Image Feature Extraction
•
Updated
•
19
•
1
AvitoTech/avibe
Text Generation
•
8B
•
Updated
•
3.29k
•
46
AvitoTech/avibe-eagle
Text Generation
•
0.4B
•
Updated
•
90
•
5
AvitoTech/avision
Image-Text-to-Text
•
7B
•
Updated
•
1.26k
•
21