A collection of Zarya text diffusion models
ai-forever PRO
ai-forever
AI & ML interests
NLP, CV, multimodal, python3, pytorch, machine learning, deep learning
Recent Activity
updated a Space 39 minutes ago
ai-forever/WebPageBench upvoted a paper 3 days ago
Closing the Loop: Practical Training Recipes for Looped Language Models updated a model 9 days ago
ai-forever/Zarya-4BOrganizations
RUMBA
Russian User Memory Benchmark: Evaluating long-context memory
Kandinsky 5.0 T2V Lite Diffusers
-
kandinskylab/Kandinsky-5.0-T2V-Lite-sft-5s-Diffusers
2B • Updated • 183 • 4 -
kandinskylab/Kandinsky-5.0-T2V-Lite-nocfg-5s-Diffusers
2B • Updated • 17 • 1 -
kandinskylab/Kandinsky-5.0-T2V-Lite-distilled16steps-5s-Diffusers
2B • Updated • 123 • 1 -
kandinskylab/Kandinsky-5.0-T2V-Lite-pretrain-5s-Diffusers
2B • Updated • 21 • 1
Wan-NABLA
Collection of finetuned models for NABLA: Neighborhood Adaptive Block-Level Attention
https://arxiv.org/abs/2507.13546
-
ai-forever/Wan2.1-T2V-14B-NABLA-0.7
Text-to-Video • 14B • Updated • 484 • 6 -
ai-forever/Wan2.1-T2V-14B-NABLA-0.5-STA-11-5-5
Text-to-Video • 14B • Updated • 449 -
ai-forever/Wan2.1-T2V-14B-NABLA-0.6-STA-11-3-3
Text-to-Video • 14B • Updated • 531 • 1 -
nablaNABLA: Neighborhood Adaptive Block-Level Attention
Paper • 2507.13546 • Published • 120
SAGE v1.1.0 release
ruELECTRA-family
SAGE v1.0.0 release
SMITH
FiMMIA
FiMMIA: scaling semantic perturbation-based membership inference across modalities.
Kandinsky 5.0
POLLUX
LLM-as-a-judge
RU-MTEB
SentenceEmbedders
Collection with our sentence embedding models, like sbert, e5 etc.
-
ai-forever/sbert_large_mt_nlu_ru
Feature Extraction • 0.4B • Updated • 19.7k • • 26 -
ai-forever/sbert_large_nlu_ru
Feature Extraction • 0.4B • Updated • 6.49k • • 106 -
ai-forever/ru-en-RoSBERTa
Feature Extraction • 0.4B • Updated • 30.3k • • 92 -
ai-forever/FRIDA
Feature Extraction • 0.8B • Updated • 694k • • 162
Zarya
A collection of Zarya text diffusion models
SMITH
RUMBA
Russian User Memory Benchmark: Evaluating long-context memory
FiMMIA
FiMMIA: scaling semantic perturbation-based membership inference across modalities.
Kandinsky 5.0 T2V Lite Diffusers
-
kandinskylab/Kandinsky-5.0-T2V-Lite-sft-5s-Diffusers
2B • Updated • 183 • 4 -
kandinskylab/Kandinsky-5.0-T2V-Lite-nocfg-5s-Diffusers
2B • Updated • 17 • 1 -
kandinskylab/Kandinsky-5.0-T2V-Lite-distilled16steps-5s-Diffusers
2B • Updated • 123 • 1 -
kandinskylab/Kandinsky-5.0-T2V-Lite-pretrain-5s-Diffusers
2B • Updated • 21 • 1
Kandinsky 5.0
Wan-NABLA
Collection of finetuned models for NABLA: Neighborhood Adaptive Block-Level Attention
https://arxiv.org/abs/2507.13546
-
ai-forever/Wan2.1-T2V-14B-NABLA-0.7
Text-to-Video • 14B • Updated • 484 • 6 -
ai-forever/Wan2.1-T2V-14B-NABLA-0.5-STA-11-5-5
Text-to-Video • 14B • Updated • 449 -
ai-forever/Wan2.1-T2V-14B-NABLA-0.6-STA-11-3-3
Text-to-Video • 14B • Updated • 531 • 1 -
nablaNABLA: Neighborhood Adaptive Block-Level Attention
Paper • 2507.13546 • Published • 120
POLLUX
LLM-as-a-judge
SAGE v1.1.0 release
RU-MTEB
ruELECTRA-family
SentenceEmbedders
Collection with our sentence embedding models, like sbert, e5 etc.
-
ai-forever/sbert_large_mt_nlu_ru
Feature Extraction • 0.4B • Updated • 19.7k • • 26 -
ai-forever/sbert_large_nlu_ru
Feature Extraction • 0.4B • Updated • 6.49k • • 106 -
ai-forever/ru-en-RoSBERTa
Feature Extraction • 0.4B • Updated • 30.3k • • 92 -
ai-forever/FRIDA
Feature Extraction • 0.8B • Updated • 694k • • 162
SAGE v1.0.0 release