mongolu

Well, it doesn't quite work in docker. Since the go build was already done , it uses it even if you afterwards set CUDA_VISIBLE_DEVICES="". I also tried creating a model...

Happy New Year! Also, it will be a lot more useful to be a runtime flag. Please🙂 It happens frequently for me to receive CUDA error OOM, especially when having...

Hi there. I'm on Win11, wsl2, docker. I've been using a lot wsl2, doing things straight inside it It worked for a while, but with time, it got pretty ugly....

And actually host ram, swap space, are directly related to wsl2, not to docker.

Chill man, you're not in production!

i think the problem here is in "Auto-GPT/autogpt/commands/execute_code.py" it needs another .parent, since commands is a directory level 3 from root. 

also, for searching files returning none, dir "auto_gpt_workspace" is added twice in the path 

also when trying to read file it uses twice the "auto_gpt_workspace"  

> I thought I'd post this here in case it helps others suffering from OOM errors as I searched and can see no mention of either "num_batch" or "n_batch" anywhere...

> > Niceee! 10x, it resolved my problem (bumping into this too, oftenly). I use 64 for num_batch now. > > Can you run a test and see if leaving...