alt Hacker NewsWhen the Unsloth quant of the flash model does appear, it should show up as unsloth/... on this page:
https://huggingface.co/models?other=base_model:quantized:zai...
Probably as:
Replies
dumbmrblah • yesterday at 5:33 PM
One thing to consider is that this version is a new architecture, so it’ll take time for Llama CPP to get updated. Similar to how it was with Qwen Next.
➕ show 1 reply
it'a a new architecture. Not yet implemented in llama.cpp
issue to follow: https://github.com/ggml-org/llama.cpp/issues/18931