moge2dvlt
da3dvlt framework with MoGe-2 ViT-L (864 tokens per view) in place of DA3MONO-LARGE; training is ongoing, newer checkpoints may be added.
Code, training / evaluation protocol and results: GitHub moge2dvlt branch. scripts/download_weights.py there downloads the newest checkpoint of this repo.
<name>.pt model state dict, <name>_opt.pt AdamW state, <name>.step global step.
| file | bytes | sha256 |
|---|---|---|
md_3722515_step7494.pt |
1706239817 | 3e6890c6798f617d7a8eedf9d7a998ac5f3feaebebb3c8f12263dad6e0ac216f |
md_3722515_step7494_opt.pt |
2719718774 | b9bfd503f2db02f99a06e621659ab480cf0cba37a0fcccf8a3a345a8c501b77a |
md_3722515_step7494.step |
4 | c522f84b7306102b5fb625ce2ac46abf7b7199c88db537a81fe42d319a8a3bc8 |
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support