Shape Error when Running Inferencer Script

[notasquid1938]

I know this repository is a bit old, but I'm hoping someone can take a look at this issue. I successfully created the vocabulary and trained the model using all the default script settings on two of my own txt files, however when I try to run the inferencer so I can use the model on a prompt I get this shape erros:

Traceback (most recent call last):
File "E:\Prompt-Generating-AI\tf-transformerxl-language-model\run_inferencer.py", line 134, in
app.run(main)
File "C:\Users\gjsho\AppData\Local\Programs\Python\Python310\lib\site-packages\absl\app.py", line 308, in run
_run_main(main, args)
File "C:\Users\gjsho\AppData\Local\Programs\Python\Python310\lib\site-packages\absl\app.py", line 254, in _run_main
sys.exit(main(argv))
File "E:\Prompt-Generating-AI\tf-transformerxl-language-model\run_inferencer.py", line 123, in main
token_id_list = inferencer.infer(tf.constant([prompt_token_ids]))
File "E:\Prompt-Generating-AI\tf-transformerxl-language-model\model_runners.py", line 251, in infer
_, memories = self._model(
File "C:\Users\gjsho\AppData\Local\Programs\Python\Python310\lib\site-packages\keras\utils\traceback_utils.py", line 67, in error_handler
raise e.with_traceback(filtered_tb) from None
File "E:\Prompt-Generating-AI\tf-transformerxl-language-model\model.py", line 176, in build
self.add_weight(name='content_bias',
ValueError: In this tf.Variable creation, the initial value's shape ((9, 8, 64)) is not compatible with the explicitly supplied shape argument ((8, 64)).