Hugging Face
Models
Datasets
Spaces
Buckets
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
anbinh39
/
MAVT_V2
Like
0
image-tokenizer
video-tokenizer
autoencoder
dinov3
License:
other
Model card
Files
Files and versions
xet
Community
Copy to bucket
main
MAVT_V2
/
image_video_conv
30.6 GB
Ctrl+K
Ctrl+K
1 contributor
History:
23 commits
anbinh39
H2-conv (3.17): conv decoder d_f 52, 8 GPU, stopped 2026-11-03
a08c83d
verified
about 7 hours ago
step10000
H2-conv (3.17) step 10000: eval tables
about 12 hours ago
step11000
H2-conv (3.17) step 11000: eval tables
about 11 hours ago
step12000
H2-conv (3.17) step 12000: eval tables
about 10 hours ago
step13000
H2-conv (3.17) step 13000: eval tables
about 9 hours ago
step14000
H2-conv (3.17) step 14000: eval tables
about 7 hours ago
step3000
H2-conv (3.17) step 3000: raw + EMA export, eval tables
about 19 hours ago
step3866
H2-conv (3.17) step 3866: raw + EMA export (training continues)
about 18 hours ago
step5000
H2-conv (3.17) step 5000: eval tables
about 17 hours ago
step6000
H2-conv (3.17) step 6000: eval tables
about 16 hours ago
step7000
H2-conv (3.17) step 7000: eval tables
about 15 hours ago
step8000
H2-conv (3.17) step 8000: eval tables
about 14 hours ago
step9000
H2-conv (3.17) step 9000: eval tables
about 13 hours ago
stop_1102
H2-conv (3.17): conv decoder d_f 52, 8 GPU, stopped 2026-11-03
about 7 hours ago