Killed

[Tsunami014]

I downloaded the repo and was super happy to see the story model work! Then I looked down and saw the chat so I went and installed it via the wget that was provided in the readme But, when I try to run it, this happened:

username@username:~/mojo/llama2.mojo$ mojo llama2.mojo tl-chat.bin \
    -r falcon \
    -z tok_tl-chat.bin \
    -n 256 -t 0 -s 100 -i "<|im_start|>user\nGive me a python function to generate Fibonacci sequence<|im_end|>\n<|im_start|>assistant\n"
num hardware threads:  4
SIMD vector width:  16
Killed

(sorry, I accidentally opened the issue before I finished typing it 😢 )

Actually, this even happens if I follow all the instructions, download again and all, in a new folder

[tairov]

Hi @Tsunami014 , thanks for your question. I can guess you don't have enough memory on the system. Mojo requires at least 8Gb RAM Also, were you able to execute llama2 on smaller models? like stories15M.bin

[Tsunami014]

I was able to run the stories15M.bin file perfectly fine. My laptop has 40GB worth of space (plenty) And I'm able to run those gpt-j files in python fine (and they're 7GB in size), so I didn't think that was any problem... Oh I see what you mean. Installed RAM 8.00 GB (7.35 GB usable) Thass a shame If only there was a way to run those files