[Bug]: Why cant I change models?

[huajitellyou]

What happened?

When I click to switch models, the progress bar will still be the original model after going through, and then an error will be reported

File "/usr/local/lib/python3.9/dist-packages/safetensors/torch.py", line 98, in load_file with safe_open(filename, framework="pt", device=device) as f: Exception: Error while deserializing header: HeaderTooLarge

Colab cell output

Loading weights [18f76d0ac4] from /content/drive/MyDrive/stable-diffusion-webui-colab/stable-diffusion-webui/models/Stable-diffusion/anything-v4.5-vae-swapped.safetensors
changing setting sd_model_checkpoint to anything-v4.5-vae-swapped.safetensors [18f76d0ac4]: Exception
Traceback (most recent call last):
  File "/content/drive/MyDrive/stable-diffusion-webui-colab/stable-diffusion-webui/modules/shared.py", line 568, in set
    self.data_labels[key].onchange()
  File "/content/drive/MyDrive/stable-diffusion-webui-colab/stable-diffusion-webui/modules/call_queue.py", line 15, in f
    res = func(*args, **kwargs)
  File "/content/drive/MyDrive/stable-diffusion-webui-colab/stable-diffusion-webui/webui.py", line 146, in <lambda>
    shared.opts.onchange("sd_model_checkpoint", wrap_queued_call(lambda: modules.sd_models.reload_model_weights()))
  File "/content/drive/MyDrive/stable-diffusion-webui-colab/stable-diffusion-webui/modules/sd_models.py", line 488, in reload_model_weights
    state_dict = get_checkpoint_state_dict(checkpoint_info, timer)
  File "/content/drive/MyDrive/stable-diffusion-webui-colab/stable-diffusion-webui/modules/sd_models.py", line 262, in get_checkpoint_state_dict
    res = read_state_dict(checkpoint_info.filename)
  File "/content/drive/MyDrive/stable-diffusion-webui-colab/stable-diffusion-webui/modules/sd_models.py", line 241, in read_state_dict
    pl_sd = safetensors.torch.load_file(checkpoint_file, device=device)
  File "/usr/local/lib/python3.9/dist-packages/safetensors/torch.py", line 98, in load_file
    with safe_open(filename, framework="pt", device=device) as f:
Exception: Error while deserializing header: HeaderTooLarge

Which colab and model(s) were you using when the error occurred?

https://huggingface.co/ckpt/anything-v4.5-vae-swapped/resolve/main/anything-v4.5-vae-swapped.safetensors

Which Public WebUI Colab URL were you using when the error occurred?

remote.moe

If you used HiRes mode when the error occurred, please provide the Hires info

No response

[Anonimouche]

Did you try using the cpkt version instead of the safetensors?