Skip to content

Hardware requirements for inference and fine tuning.  #14

Description

@Vipitis

Hey,

I am finishing a project on evaluating code language models on "creative" programming (shadercode). Just yesterday I finished fine-tuning sanatacoder on three different datasets to evaluate on my metric.

Now this new project popped up but it's vastly larger. Prohibitively so. I was unable to run 6B models on the RTX A5000 I have access to.
For finetuning santacoder (no_fp16, batch_size 2 and sequence length of 2048) 97% of the 24GB VRAM was used using a slightly adapted version of the provided script.

Do you have any numbers on what requirements there are for PEFT on this model? And is there a set way to run inference with the hardware I listed?

Thanks for releasing yet another interesting model!

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions