moge2dvlt
da3dvlt framework with MoGe-2 ViT-L (864 tokens per view) in place of DA3MONO-LARGE; training stopped at global step 13031 (md_3725959_step13031, the newest file here).
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 |
md_3725959_step13031.pt |
1706233310 | 1cd90bb1727bccd6aa17adeb3410f164ec488891c02c0eea07c99bf08852b35c |
md_3725959_step13031_opt.pt |
2719704103 | 25d170455ce0225c8a1a33e3943751b62862598b554fe225de6aa54da6422a93 |
md_3725959_step13031.step |
5 | 04b102996714e9d04e206c5de47ed1fd895f6a562be55f4a775e6c3d291e6898 |
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support