Illegal instruction (core dumped)

[llagerlof]

I am aware of the issue 63, but this error is happening in a real machine, not a VM.

My specs:

• OS: Fedora 36
• Kernel: 6.2.8
• CPU: AMD FX(tm)-6300 Six-Core Processor
• RAM: 16GB
• GPU: GeForce GTX 1050 Ti
• GPU memory: 4GB

gpt4all/chat on  main 
$ ./gpt4all-lora-quantized-linux-x86
main: seed = 1681391007
llama_model_load: loading model from 'gpt4all-lora-quantized.bin' - please wait ...
llama_model_load: ggml ctx size = 6065.35 MB
llama_model_load: memory_size =  2048.00 MB, n_mem = 65536
llama_model_load: loading model part 1/1 from 'gpt4all-lora-quantized.bin'
llama_model_load: .................................... done
llama_model_load: model size =  4017.27 MB / num tensors = 291

system_info: n_threads = 4 / 6 | AVX = 1 | AVX2 = 1 | AVX512 = 0 | FMA = 1 | NEON = 0 | ARM_FMA = 0 | F16C = 1 | FP16_VA = 0 | WASM_SIMD = 0 | BLAS = 0 | SSE3 = 1 | VSX = 0 | 
main: interactive mode on.
sampling parameters: temp = 0.100000, top_k = 40, top_p = 0.950000, repeat_last_n = 64, repeat_penalty = 1.300000


Illegal instruction (core dumped)

$

[qinidema]

@llagerlof see #82, i.e. that comment and this comment.

[reddiamond1234]

@llagerlof see #82, i.e. that comment and this comment.

my CPU doesnt have AVX. didnt work after i compiled...

[niansa]

Should be solved by now