tried following the steps, failed

#1
by dataf3l - opened

llama_model_load: error loading model: done_getting_tensors: wrong number of tensors; expected 578, got 470
llama_load_model_from_file: failed to load model
llama_init_from_gpt_params: error: failed to load model '../models/granite-8b-code-base.Q8_0.gguf'
main: error: unable to load model
(venv) ➜ llama.cpp git:(master) ./main -m ../models/granite-8b-code-base.Q8_0.gguf -p 'hi' -c 2048

not sure how to proceed, I cloned downloaded llama.cpp, not sure if using right branch atm.

Same here, this is not working even in latest LM Studio!

Your need to confirm your account before you can post a new comment.

Sign up or log in to comment