'llama.cpp/quantize' does not exist.

[LMseventeen]

Unsloth: Installing llama.cpp. This might take 3 minutes...
Traceback (most recent call last):
File "/root/autodl-tmp/unsloth-custom/main.py", line 115, in
model.push_to_hub_gguf("Wuhao17/testserver", tokenizer, token = "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")
File "/root/autodl-tmp/unsloth-custom/.venv/lib/python3.10/site-packages/unsloth/save.py", line 2034, in unsloth_push_to_hub_gguf
all_file_locations, want_full_precision = save_to_gguf(
File "/root/autodl-tmp/unsloth-custom/.venv/lib/python3.10/site-packages/unsloth/save.py", line 1085, in save_to_gguf
raise RuntimeError(
RuntimeError: Unsloth: The file ('llama.cpp/llama-quantize' or 'llama.cpp/llama-quantize.exe' if you are on Windows WSL) or 'llama.cpp/quantize' does not exist.
But we expect this file to exist! Maybe the llama.cpp developers changed the name or check extension of the llama-quantize file.

[claree007]

I am getting the same error. When manually installing llama.cpp using below steps:

cmake -B build
cmake --build build --config Release

the installation does not contain llama-quantize. Below ss contains the folder contents when llama.cpp is manually installed:

But if I don't manually install llama.cpp and let unsloth automatically install it while saving model to GGUF, I don't get this error and I can see the required files.

[hai-dchu]

Isn't the llama-quantize inside llama.cpp/build/bin/? I suggest checking if there is such folder.