Orca q2_k and Llama.cpp
#1
by
Jeximo
- opened
Hi @TheBloke ,
Thanks for your work.
I expected orca-mini-v2_7b.ggmlv3.q2_K.bin to run in llama.cpp. Here'a the error:
main: build = 0 (unknown)
main: seed = 1688477511
llama.cpp: loading model from /data/data/com.termux/files/home/orca-mini-v2_7b.ggmlv3.q2_K.bin
error loading model: llama.cpp: tensor '' should not be 0-dimensional
llama_load_model_from_file: failed to load model
llama_init_from_gpt_params: error: failed to load model '/data/data/com.termux/files/home/orca-mini-v2_7b.ggmlv3.q2_K.bin'
main: error: unable to load model
Does this model load as expected for your system?
Edit: my download was corrupted, so I'm redownloasing now and expect it will work fine.
Thanks.
Jeximo
changed discussion status to
closed