Bug: Can't quantize in gguf q5_k_m a mamba architecture codestral

[Volko61]

What happened?

Error: Error converting to fp16: b'INFO:hf-to-gguf:Loading model: mamba-codestral-7B-v0.1\nTraceback (most recent call last):\n File "/home/user/app/llama.cpp/convert_hf_to_gguf.py", line 3673, in \n main()\n File "/home/user/app/llama.cpp/convert_hf_to_gguf.py", line 3645, in main\n model_architecture = hparams["architectures"][0]\nKeyError: 'architectures'\n'

Name and Version

latest (hf space)

What operating system are you seeing the problem on?

Other? (Please let us know in description)

Relevant log output

Error: Error converting to fp16: b'INFO:hf-to-gguf:Loading model: mamba-codestral-7B-v0.1\nTraceback (most recent call last):\n File "/home/user/app/llama.cpp/convert_hf_to_gguf.py", line 3673, in \n main()\n File "/home/user/app/llama.cpp/convert_hf_to_gguf.py", line 3645, in main\n model_architecture = hparams["architectures"][0]\nKeyError: 'architectures'\n'

![image](https://github.com/user-attachments/assets/6f1ab039-754d-4c6c-8bb8-274c0c99ca13)

[NextGenOP]

#8519 related to this

[github-actions]

This issue was closed because it has been inactive for 14 days since being marked as stale.