error in runing

[NazilaPourhaji]

hello,
I received the following error:

"TypeError: Exception encountered when calling CLIPEncoderLayer.call().

Could not automatically infer the output shape / dtype of 'clip_encoder_layer' (of type CLIPEncoderLayer). Either the CLIPEncoderLayer.call() method is incorrect, or you need to implement the CLIPEncoderLayer.compute_output_spec() / compute_output_shape() method. Error encountered:

Exception encountered when calling CLIPAttention.call().

pred must not be a Python bool

Arguments received by CLIPAttention.call():
• inputs=tf.Tensor(shape=(None, 77, 768), dtype=float32)
• attention_mask=None

Arguments received by CLIPEncoderLayer.call():
• args=('<KerasTensor shape=(None, 77, 768), dtype=float32, sparse=False, name=keras_tensor_60>',)
• kwargs=<class 'inspect._empty'>"

for the command
"unconditional_context = self.text_encoder.predict_on_batch( [unconditional_tokens, self._get_pos_ids()])"

in the function "_get_unconditional_context" in the file "stable_diffusion.py".

Please help me to run this code.

Thanks.