Error on collab saving GGUF Mistral Small 22b

Unsloth: Kaggle/Colab has limited disk space. We need to delete the downloaded
model which will save 4-16GB of disk space, allowing you to save on Kaggle/Colab.
Unsloth: Will remove a cached repo with size 44.5G
Unsloth: Merging 4bit and LoRA weights to 16bit...
Unsloth: Will use up to 58.42 out of 83.48 RAM for saving.
Unsloth: Saving model... This might take 5 minutes ...
48%|████▊ | 27/56 [00:01<00:00, 34.08it/s]
We will save to Disk and not RAM now.
100%|██████████| 56/56 [00:57<00:00, 1.02s/it]
Unsloth: Saving tokenizer... Done.
Done.
Unsloth: Converting mistral model. Can use fast conversion = True.
==((====))== Unsloth: Conversion from QLoRA to GGUF information
\ /| [0] Installing llama.cpp might take 3 minutes.
O^O/ _/ \ [1] Converting HF to GGUF 16bits might take 3 minutes.
\ / [2] Converting GGUF 16bits to ['q4_k_m', 'q4_0', 'q5_k_m'] might take 10 minutes each.
"-____-" In total, you will have to wait at least 16 minutes.

Unsloth: Installing llama.cpp. This might take 3 minutes...
Unsloth: CMAKE detected. Finalizing some steps for installation.
Unsloth: [1] Converting model at AlSamCur123/MistralSmall22bAlpaca into bf16 GGUF format.
The output location will be /content/AlSamCur123/MistralSmall22bAlpaca/unsloth.BF16.gguf
This might take 3 minutes...

TypeError Traceback (most recent call last)
/tmp/ipython-input-3191303488.py in <cell line: 0>()
15 # Save to multiple GGUF options - much faster if you want multiple!
16 if True:
---> 17 model.push_to_hub_gguf(
18 "AlSamCur123/MistralSmall22bAlpaca", # Change hf to your username!
19 tokenizer,

4 frames
/usr/local/lib/python3.12/dist-packages/google/protobuf/descriptor.py in new(cls, name, index, number, type, options, serialized_options, create_key)
918 type=None, # pylint: disable=redefined-builtin
919 options=None, serialized_options=None, create_key=None):
--> 920 _message.Message._CheckCalledFromGeneratedFile()
921 # There is no way we can build a complete EnumValueDescriptor with the
922 # given parameters (the name of the Enum is not known, for example).

TypeError: Descriptors cannot be created directly.
If this call came from a _pb2.py file, your generated code is out of date and must be regenerated with protoc >= 3.19.0.
If you cannot immediately regenerate your protos, some other possible workarounds are:

1. Downgrade the protobuf package to 3.20.x or lower.
2. Set PROTOCOL_BUFFERS_PYTHON_IMPLEMENTATION=python (but this will use pure-Python parsing and will be much slower).

More information: https://developers.google.com/protocol-buffers/docs/news/2022-05-06#python-updates