wst2001

/

OctGPT

like 5

Hello!

Great paper! I am looking to try the models locally, but I am getting this error:

(octgpt) root@C.20625699:/home//three-gen-subnet-trellis/octgpt$ python main_octgpt.py     --config configs/Objaverse/objaverse_octar_text.yaml     SOLVER.run generate     SOLVER.logdir logs/obja_text     SOLVER.ckpt saved_ckpt/octgpt_objv_text.pth     MODEL.vqvae_ckpt saved_ckpt/vqvae_large_objv_bsq32.pth     DATA.test.text_prompt "A 3D model of a Pokémon character."
Using a slow image processor as `use_fast` is unset and a slow processor was saved with this model. `use_fast=True` will be the default behavior in v4.52, even if the model was saved with a slow processor. This will result in minor differences in outputs. You'll still be able to use a slow processor with `use_fast=False`.
Traceback (most recent call last):
  File "/home//three-gen-subnet-trellis/octgpt/main_octgpt.py", line 227, in <module>
    OctGPTSolver.main()
  File "/home//miniconda/envs/octgpt/lib/python3.10/site-packages/thsolver/solver.py", line 456, in main
    cls.worker(0, FLAGS)
  File "/home//miniconda/envs/octgpt/lib/python3.10/site-packages/thsolver/solver.py", line 445, in worker
    the_solver.run()
  File "/home//miniconda/envs/octgpt/lib/python3.10/site-packages/thsolver/solver.py", line 420, in run
    eval('self.%s()' % self.FLAGS.SOLVER.run)
  File "<string>", line 1, in <module>
  File "/home//three-gen-subnet-trellis/octgpt/main_octgpt.py", line 135, in generate
    self.config_model()
  File "/home//miniconda/envs/octgpt/lib/python3.10/site-packages/thsolver/solver.py", line 102, in config_model
    model = self.get_model(flags)
  File "/home//three-gen-subnet-trellis/octgpt/main_octgpt.py", line 53, in get_model
    checkpoint = torch.load(
  File "/home//miniconda/envs/octgpt/lib/python3.10/site-packages/torch/serialization.py", line 1383, in load
    raise pickle.UnpicklingError(_get_wo_message(str(e))) from None
_pickle.UnpicklingError: Weights only load failed. Re-running `torch.load` with `weights_only` set to `False` will likely succeed, but it can result in arbitrary code execution. Do it only if you got the file from a trusted source.
Please file an issue with the following so that we can make `weights_only=True` compatible with your use case: WeightsUnpickler error: Unsupported operand 118

Check the documentation of torch.load to learn more about types accepted by default with weights_only https://pytorch.org/docs/stable/generated/torch.load.html.

will the right weights be uploaded soon?

Looking forward to your response.