Compile bug:

[sraouser]

Git commit

https://github.com/ggml-org/llama.cpp
Branch:master

Operating systems

Windows

GGML backends

CUDA

Problem description & steps to reproduce

Ref:

1. https://gorilla.cs.berkeley.edu/blogs/5_how_to_gorilla.html#integrate-third-party
2. https://github.com/ggml-org/llama.cpp
   Step V, B(5b)
   Command:
   Run llama.cpp/finetune --model-base the-model-you-downloaded.gguf --train-data your-training-data.txt(Ref2)

The ref 2 git repo has no finetune file at all. Please suggest as to how I can get that.
Thanks,
Suma

First Bad Commit

No response

Compile command

Run llama.cpp/finetune --model-base the-model-you-downloaded.gguf --train-data your-training-data.txt

Relevant log output

No file named finetune in the git repo. Please suggest.

[fairydreaming]

Unfortunately the finetune util (later renamed to llama-finetune) was removed from the project several months ago in PR #8669. What you can do is to use some older release that was created before the removal (Jul 25, 2024). But in this PR some problems with finetune are mentioned, I'm not sure if it even worked correctly at this point.

[github-actions]

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