Why does the model quantization prompt KILLED at the end?

qwopqwop200 / GPTQ-for-LLaMa

4 bits quantization of LLaMA using GPTQ

Apache License 2.0

2.98k stars 457 forks source link

Open g558800 opened 1 year ago

g558800 commented 1 year ago

Why does the model quantization prompt KILLED at the end? 无标题

msalhab96 commented 1 year ago

It's a RAM issue, try to increase the RAM size, or add a memory swap

g558800 commented 1 year ago

Resolved. thanks