tairov / llama2.mojo

Inference Llama 2 in one file of pure 🔥
https://www.modular.com/blog/community-spotlight-how-i-built-llama2-by-aydyn-tairov
MIT License
2.09k stars 140 forks source link

it is taking python 3.6 insted of 3.9.18 #33

Closed y3rawat closed 11 months ago

y3rawat commented 11 months ago

/home/y3rawat/.modular/pkg/packages.modular.com_mojo/bin/mojo /home/y3rawat/mojo/llama2.mojo /home/y3rawat/mojo/llama2.mojo:10:6: error: unable to locate module 'read' from read import BufReader, File ^ /home/y3rawat/.modular/pkg/packages.modular.com_mojo/bin/mojo: error: failed to parse the provided Mojo (python38) y3rawat@y3rawat-ASUS-TUF-Gaming-F15-FX507ZC4-FX507ZC4:~/mojo$

tairov commented 11 months ago

hi @ysh-rawat-11 are you sure you have pulled all files from this repo?

y3rawat commented 11 months ago

(python38) y3rawat@y3rawat-ASUS-TUF-Gaming-F15-FX507ZC4-FX507ZC4:~/Documents/llama2.mojo-master$ /home/y3rawat/.modular/pkg/packages.modular.com_mojo/bin/mojo /home/y3rawat/Documents/llama2.mojo-master/llama2.mojo num hardware threads: 12 SIMD vector width: 16 Usage: mojo llama2.mojo [options] Example: mojo llama2.mojo stories15M.bin -s 99 -n 256 -t 0.5 -i "Llama is an animal" Options: -s random seed, default time.now() -t temperature in [0,1.0], default 1.0 -n number of steps to run for, default 256. 0 = max_seq_len -i input prompt -z tokenizer path -r rope architecture, default 'llama' for llama rope, 'falcon' for falcon rope (python38) y3rawat@y3rawat-ASUS-TUF-Gaming-F15-FX507ZC4-FX507ZC4:~/Documents/llama2.mojo-master$ mojo llama2.mojo stories15M.bin -s 100 -n 256 -t 0.5 -i "Llama is an animal" Invalid command "llama2.mojo". (python38) y3rawat@y3rawat-ASUS-TUF-Gaming-F15-FX507ZC4-FX507ZC4:~/Documents/llama2.mojo-master$

tairov commented 11 months ago

I guess you have installed some wrong binary instead of mojo sdk..