Brian
do we use valgrind here and should we?
@stevegrubb looks like it might take a while for https://github.com/ggerganov/llama.cpp/pull/6289 to be merged in. You may want to check if any of the leaks fixes from there is directly related...
Is this bug still present? Just chasing up older PRs to make sure it's not obsolete
@zhouwg attempted to resolve the conflict, but you may want to consider rebasing anyway.
@zhouwg you mean writing directly to master? Well no. But been helping out at least with triaging, which should still be helpful? If you noticed, I've been putting labels everywhere...
Don't forget https://github.com/ggerganov/llama.cpp/wiki as well, I've reorganised the sidebar to be a bit clearer. The wiki will be useful for information that is a bit too technical for wikipedia.
``` $ ./build/bin/tokenizer-verifier ./models/ggml-vocab-aquila.gguf WARNING: Behavior may be unexpected when allocating 0 bytes for ggml_calloc! llama_model_loader: loaded meta data with 18 key-value pairs and 0 tensors from ./models/ggml-vocab-aquila.gguf (version GGUF...
> If it helps, we follow somewhat similar (but not exhaustive) in the `gguf-my-repo` quantisation space: https://huggingface.co/spaces/ggml-org/gguf-my-repo/blob/main/app.py#L67 > > Standardisation in file name is always a great move! Had a...
@julien-c do you have a preference when it comes to parsing filenames? I'm basically treating it as a sort of `-` dash separated value (in which case, I should probably...
Thanks for the historical context. I might have gotten a bit crazy here, but I've ended up mapping each enum name to the tensor type description and the historical context...