gpt4all
gpt4all copied to clipboard
Illegal instruction error
I'm facing this error on Ubuntu 22 build,
./gpt4all-lora-quantized-linux-x86 -m gpt4all-lora-quantized.bin main: seed = 1681884509 llama_model_load: loading model from 'gpt4all-lora-quantized.bin' - please wait ... Illegal instruction (core dumped)
As you can see it is unable to load the gpt4all-lora-quantized.bin file and returns with this error. Any fix ?
Recompile it manually. It will be slow though because the instruction you're missing is AVX or AVX2.
ok
Stale, please open a new, updated issue if this is still relevant to you.
Non-AVX support won't happen.