safetensors_rust.SafetensorError: Error while deserializing header: HeaderTooLarge

[kwikik]

i install everything correctly and when i want to run an inference , i get this error.
People on the net with the same error told me that it can be corrupted file so i download everything again ( multiple time and i keep getting this error) here the full error message

Traceback (most recent call last):
File "/home/azureuser/localfiles/MagicTime/inference_magictime.py", line 249, in
main(args)
File "/anaconda/envs/magictime/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/home/azureuser/localfiles/MagicTime/inference_magictime.py", line 61, in main
text_encoder = CLIPTextModel.from_pretrained(model_config.pretrained_model_path, subfolder="text_encoder").cuda()
File "/anaconda/envs/magictime/lib/python3.10/site-packages/transformers/modeling_utils.py", line 3284, in from_pretrained
with safe_open(resolved_archive_file, framework="pt") as f:
safetensors_rust.SafetensorError: Error while deserializing header: HeaderTooLarge

[SHYuanBest]

Thank you for your interest. I have never encountered this error. Maybe you can confirm whether the version information of the package is consistent with ours, or try to reconfigure the environment.

[SHYuanBest]

It seems that there is a problem with your torch or transformers library. You can try to reinstall the same version as ours.

[kwikik]

It seems that there is a problem with your torch or transformers library. You can try to reinstall the same version as ours.

I already check the environnement but i will reinstall it from scratch i come home from work thx for your reply

[lckj2009]

My server is already running MagicTime normally, but there is no model called "safetendersorust.Safetensor" on my server. Please check when this model was installed during the installation process

[truedat101]

Maybe a duplicate of #21 . Sorry I posted a dup! Try making sure git-lfs is installed. Then redo your installation. Easiest way is to do "git checkout ckpts" to restore order. Note, issues with these scripts #23 .