dataequity

/

mistral-7b-instruct-v0.2.Q5_K_M.gguf

like 1

llm_load_tensors: tensor 'token_embd.weight' (q5_K) (and 290 others) cannot be used with preferred buffer type CPU_AARCH64, using CPU instead

can someone please explain what this means? I have looked everywhere but did not find a straightforward answer. I am trying to make sure my mistral model is using the gpu. Thanks in advance