Andrews Cordolino Sobral
Andrews Cordolino Sobral
Hello guys, I am also interested to see how to run LLaMA (e.g. 7B model) on Mac M1 or M2, any solution?
Hello guys, I am also interested to see how to run LLaMA (e.g. 7B model) on Mac M1 or M2, any solution until now?
Hello @carlos-gemmell , Why you put `--nproc_per_node 1` in the first example and `--nproc_per_node 2` in the second one?
@carlos-gemmell sorry, ignore my last message, I see you changed the model from 7B to 13B, so it's normal. So, the inference worked for 7B but not for 13B...
@carlos-gemmell what happens if you do? ``` $ CUDA_VISIBLE_DEVICES="0" torchrun --nproc_per_node 1 example.py --ckpt_dir checkpoints/7B --tokenizer_path checkpoints/tokenizer.model ``` instead of `$ CUDA_VISIBLE_DEVICES="0,1"`
Same for me, but in my case I have 2x RTX 2070 (8Gb each) 16Gb in total. How could we use multiple gpus? ``` # | Model | MP |...
Just got approved, downloaded weights successfully.
Hello @DamienKoala, Thank you for bringing this issue to our attention. I suspect the problem may be related to the Python version. I haven't had the opportunity to test it...
Thank you very much @DamienKoala , i need to check this when I have time. Best regards, Andrews