Xenova

/

llama2.c-stories15M

like 6

Hello，After trying to download a stories15M model on hf, I quantized it,
As shown in these two files。

then . I use " python export.py stories_q80.bin --version 2 --hf .\model" That worked and it also succeeded for runq.c, but after executing” ./runq .stories_q80.bin -n 20 -i 'one day' “at the end, the code would just output my prompt one day and end the program