Error: llama runner process has terminated: error loading model: missing tensor 'output.weight' llama_load_model_from_file: failed to load model
#1
by
dbmuller
- opened
Error: llama runner process has terminated: error loading model: missing tensor 'output.weight'
llama_load_model_from_file: failed to load model
I had the same problem when I tried converting it.
Also I take it this might need a newer build of llama.cpp and maybe won't work in ollama yet?
I've tested it with llama.cpp build from the branch I've shared on the model card:
At the model page https://ollama.com/library/phi4-mini:3.8b there is the following note:
Note: this model requires Ollama 0.5.13 which is currently in pre-release.
I can confirm that updating to the latest version of Ollama fix this issue :)