Florence2Model get error report

### Expected Behavior

How can I fix this problem.

### Actual Behavior

Florence2Model get error report while I use ComfyUI on CogVideo Generate video.

### Steps to Reproduce

Use workflow "IT'S ALIVE! | Ultimate IMAGE to VIDEO suite | LTX/Cog/PyramidFlow", it can be download from : https://civitai-delivery-worker-prod.5ac0637cfd0766c97916cefa3764fbdf.r2.cloudflarestorage.com/default/1033802/itsALIVEV902.zvHc.zip?X-Amz-Expires=86400&response-content-disposition=attachment%3B%20filename%3D%22itsALIVEUltimateIMAGETo_v902.zip%22&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=e01358d793ad6966166af8b3064953ad/20250304/us-east-1/s3/aws4_request&X-Amz-Date=20250304T051921Z&X-Amz-SignedHeaders=host&X-Amz-Signature=3e0b610935bf54141f2da9db4b6fb0b199285e29c51ad9b1e3f8aaddc6ec4f9d
you can get description on : https://civitai.com/models/866210/its-alive-or-ultimate-image-to-video-suite-or-ltxcogpyramidflow?modelVersionId=1122726

### Debug Logs

```powershell
WARNING: SystemNotification.IS_CHANGED() missing 1 required positional argument: 'self'
WARNING: SystemNotification.IS_CHANGED() missing 1 required positional argument: 'self'
Closest bucket size: 448x576
# 😺dzNodes: LayerStyle -> ImageBlendAdvanceV2 Processed 1 image(s).
Florence2 using sdpa for attention
No flash_attn import to remove
!!! Exception during processing !!! Trying to set a tensor of shape torch.Size([1026, 1024]) in "weight" (which has shape torch.Size([4098, 1024])), this looks incorrect.
Traceback (most recent call last):
File "D:\win10_SD\comfyUI\ComfyUIKelvinMini_HY_V250301\ComfyUI\execution.py", line 327, in execute
output_data, output_ui, has_subgraph = get_output_data(obj, input_data_all, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\win10_SD\comfyUI\ComfyUIKelvinMini_HY_V250301\ComfyUI\execution.py", line 202, in get_output_data
return_values = _map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True, execution_block_cb=execution_block_cb, pre_execute_cb=pre_execute_cb)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\win10_SD\comfyUI\ComfyUIKelvinMini_HY_V250301\ComfyUI\execution.py", line 174, in _map_node_over_list
process_inputs(input_dict, i)
File "D:\win10_SD\comfyUI\ComfyUIKelvinMini_HY_V250301\ComfyUI\execution.py", line 163, in process_inputs
results.append(getattr(obj, func)(**inputs))
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\win10_SD\comfyUI\ComfyUIKelvinMini_HY_V250301\ComfyUI\custom_nodes\comfyui-florence2\nodes.py", line 101, in loadmodel
model = AutoModelForCausalLM.from_pretrained(model_path, attn_implementation=attention, device_map=device, torch_dtype=dtype,trust_remote_code=True)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\win10_SD\comfyUI\ComfyUIKelvinMini_HY_V250301\condaEnvMiniComfyUI\Lib\site-packages\transformers\models\auto\auto_factory.py", line 559, in from_pretrained
return model_class.from_pretrained(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\win10_SD\comfyUI\ComfyUIKelvinMini_HY_V250301\condaEnvMiniComfyUI\Lib\site-packages\transformers\modeling_utils.py", line 262, in _wrapper
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "D:\win10_SD\comfyUI\ComfyUIKelvinMini_HY_V250301\condaEnvMiniComfyUI\Lib\site-packages\transformers\modeling_utils.py", line 4319, in from_pretrained
) = cls._load_pretrained_model(
^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\win10_SD\comfyUI\ComfyUIKelvinMini_HY_V250301\condaEnvMiniComfyUI\Lib\site-packages\transformers\modeling_utils.py", line 4897, in _load_pretrained_model
new_error_msgs, offload_index, state_dict_index = _load_state_dict_into_meta_model(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "D:\win10_SD\comfyUI\ComfyUIKelvinMini_HY_V250301\condaEnvMiniComfyUI\Lib\site-packages\transformers\modeling_utils.py", line 896, in _load_state_dict_into_meta_model
set_module_tensor_to_device(model, param_name, param_device, **set_module_kwargs)
File "D:\win10_SD\comfyUI\ComfyUIKelvinMini_HY_V250301\condaEnvMiniComfyUI\Lib\site-packages\accelerate\utils\modeling.py", line 287, in set_module_tensor_to_device
raise ValueError(
ValueError: Trying to set a tensor of shape torch.Size([1026, 1024]) in "weight" (which has shape torch.Size([4098, 1024])), this looks incorrect.

Prompt executed in 1.56 seconds
```

### Other

_No response_