Fix convert script for non-hf GLM4 checkpoints

[Tianyue-Zhao]

In #10573, support was added for HF variants of the GLM-4-9B model.
However, the edits to the conversion script broke the conversion for non-HF checkpoints.
This MR simply fixes this so that the conversion script works with both.

• I have read the contributing guidelines
• Self-reported review complexity:
  • Low
  • Medium
  • High

Current master branch:

~/llama.cpp# python convert_hf_to_gguf.py ../glm-4-9b
INFO:hf-to-gguf:Loading model: glm-4-9b
INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only
INFO:hf-to-gguf:Exporting model...
...
INFO:hf-to-gguf:Set meta model
INFO:hf-to-gguf:Set model parameters
Traceback (most recent call last):
  File "/root/llama.cpp/convert_hf_to_gguf.py", line 5666, in <module>
    main()
  File "/root/llama.cpp/convert_hf_to_gguf.py", line 5660, in main
    model_instance.write()
  File "/root/llama.cpp/convert_hf_to_gguf.py", line 459, in write
    self.prepare_metadata(vocab_only=False)
  File "/root/llama.cpp/convert_hf_to_gguf.py", line 449, in prepare_metadata
    self.set_gguf_parameters()
  File "/root/llama.cpp/convert_hf_to_gguf.py", line 5077, in set_gguf_parameters
    self.gguf_writer.add_block_count(self.hparams.get("num_layers", self.hparams["num_hidden_layers"]))
KeyError: 'num_hidden_layers'

After fix:
Confirmed that both python convert_hf_to_gguf.py ../glm-4-9b and python convert_hf_to_gguf.py ../glm-4-9b-hf work without issue.