Eugenio Culurciello

Results 10 comments of Eugenio Culurciello

same here...

it looks like the frame dump load option is gone?

yes I had this problem too: the vars are saved as cuda tensors, so you need to use cutorch and cunn to load them... it should save in float and...

@karpathy we usually do things like that. Write a CPU only model and re-ship to GPU when needed. It is nice to have it that way because we might be...

I also would love to know how to render or visualize

what do you recommend me to do to get the alignment? I need to be able to project on the same space with 2 runs of data.

I tried to pass floats and the results were incorrect. Did you try or did I make a mistake?

Hi Laurens van der Maaten, do you still have a plan to used Floats, or should we look into it?

I spent a lot of time on this... but the solution was to add this line `export OLLAMA_HOST=http://host.docker.internal:11434` to your bash profile