llama_model_load: error loading model: error loading model architecture: unknown model architecture: 'gemma2'
#1
by
cloudyu
- opened
I update llama.cpp ,but it doesn't work
It's not merged yet, need to use the PR
It's merged to the master branch now, so cloning/pulling master should be enough.
In case you want to fix the commit hash:
$ git clone https://github.com/ggerganov/llama.cpp
$ cd llama.cpp
$ git checkout e57dc62057d41211ac018056c19c02cd544694df
By the way, awesome work @bartowski !
just updated it to the official release with it, good looking out though thanks!
solved. thanks.
cloudyu
changed discussion status to
closed