model failed to load error when trying to use merged model for subsequent merge

[entropyembrace]

Stable diffusion model failed to load
Substituting empty model_c with model_a
model A : Merging_MBW_01_waiANIHENTAIPONLYXL_v40_darkPhotoPony_v30Flux.fp16
model B : bemypony_Photo3
model C : Merging_MBW_01_waiANIHENTAIPONLYXL_v40_darkPhotoPony_v30Flux.fp16
alpha,beta : (0.5, 0.25)
weights_alpha :
weights_beta :
mode : Weight sum
MBW : False
CalcMode : normal
Elemental :
Weights Seed : 51039979
Off : ([], '')
Adjust :
Loading weights [bemypony_Photo3] from file
Loading weights [Merging_MBW_01_waiANIHENTAIPONLYXL_v40_darkPhotoPony_v30Flux.fp16] from file
Stage 1/2: 100%|███████████████████████████████████████████████████████████████████| 2515/2515 [00:28<00:00, 87.06it/s]
Stage 2/2: 100%|███████████████████████████████████████████████████████████████| 2515/2515 [00:00<00:00, 360182.83it/s]
Creating model from config: D:\Users\Tera\Automatic1111\repositories\generative-models\configs\inference\sd_xl_base.yaml
Traceback (most recent call last):
File "D:\Users\Tera\Automatic1111\venv\lib\site-packages\gradio\routes.py", line 488, in run_predict
output = await app.get_blocks().process_api(
File "D:\Users\Tera\Automatic1111\venv\lib\site-packages\gradio\blocks.py", line 1431, in process_api
result = await self.call_function(
File "D:\Users\Tera\Automatic1111\venv\lib\site-packages\gradio\blocks.py", line 1103, in call_function
prediction = await anyio.to_thread.run_sync(
File "D:\Users\Tera\Automatic1111\venv\lib\site-packages\anyio\to_thread.py", line 33, in run_sync
return await get_asynclib().run_sync_in_worker_thread(
File "D:\Users\Tera\Automatic1111\venv\lib\site-packages\anyio_backends_asyncio.py", line 877, in run_sync_in_worker_thread
return await future
File "D:\Users\Tera\Automatic1111\venv\lib\site-packages\anyio_backends_asyncio.py", line 807, in run
result = context.run(func, *args)
File "D:\Users\Tera\Automatic1111\venv\lib\site-packages\gradio\utils.py", line 707, in wrapper
response = f(*args, **kwargs)
File "D:\Users\Tera\Automatic1111\extensions\sd-webui-supermerger\scripts\mergers\mergers.py", line 131, in smergegen
load_model(checkpoint_info, already_loaded_state_dict=theta_0)
File "D:\Users\Tera\Automatic1111\modules\sd_models.py", line 845, in load_model
load_model_weights(sd_model, checkpoint_info, state_dict, timer)
File "D:\Users\Tera\Automatic1111\modules\sd_models.py", line 440, in load_model_weights
model.load_state_dict(state_dict, strict=False)
File "D:\Users\Tera\Automatic1111\modules\sd_disable_initialization.py", line 223, in
module_load_state_dict = self.replace(torch.nn.Module, 'load_state_dict', lambda *args, **kwargs: load_state_dict(module_load_state_dict, *args, **kwargs))
File "D:\Users\Tera\Automatic1111\modules\sd_disable_initialization.py", line 221, in load_state_dict
original(module, state_dict, strict=strict)
File "D:\Users\Tera\Automatic1111\venv\lib\site-packages\torch\nn\modules\module.py", line 2138, in load_state_dict
load(self, state_dict)
File "D:\Users\Tera\Automatic1111\venv\lib\site-packages\torch\nn\modules\module.py", line 2126, in load
load(child, child_state_dict, child_prefix)
File "D:\Users\Tera\Automatic1111\venv\lib\site-packages\torch\nn\modules\module.py", line 2126, in load
load(child, child_state_dict, child_prefix)
File "D:\Users\Tera\Automatic1111\venv\lib\site-packages\torch\nn\modules\module.py", line 2126, in load
load(child, child_state_dict, child_prefix)
[Previous line repeated 1 more time]
File "D:\Users\Tera\Automatic1111\venv\lib\site-packages\torch\nn\modules\module.py", line 2120, in load
module._load_from_state_dict(
File "D:\Users\Tera\Automatic1111\modules\sd_disable_initialization.py", line 225, in
linear_load_from_state_dict = self.replace(torch.nn.Linear, '_load_from_state_dict', lambda *args, **kwargs: load_from_state_dict(linear_load_from_state_dict, *args, **kwargs))
File "D:\Users\Tera\Automatic1111\modules\sd_disable_initialization.py", line 191, in load_from_state_dict
module.parameters[name] = torch.nn.parameter.Parameter(torch.zeros_like(param, device=device, dtype=dtype), requires_grad=param.requires_grad)
File "D:\Users\Tera\Automatic1111\venv\lib\site-packages\torch_meta_registrations.py", line 4516, in zeros_like
res.fill(0)
RuntimeError: "fill_cpu" not implemented for 'Float8_e4m3fn'

[entropyembrace]

The issue seems to be caused by using the Save Current Merge (fp16 only) button. I bypassed the issue by using the save model option and clicking merge again to save instead.

other options selected remained the same safetensors, fp16, save metadata, prune