Full fine-tuning with llama.cpp

[RonanKMcGovern]

When using GGUF and llama.cpp, is there a specific vocab file I should use, or can I use "ggml-vocab-llama.gguf"?

The number of kv groups is different in TinyLlama so I suspect that I need to use a custom vocab file, but I'm unsure.

I've been trying to fine-tune but the model isn't loading correctly. I've posted the training script on the llama.cpp repo here.