I want to extract and process the metadata from PNG images and the first line of .safetensors files for LLM’s and LoRA’s. I could spend ages farting around with sed or awk but formats of files are constantly changing. I’d like a faster way to see a summary of training and a few other details when they are available.

  • @[email protected]
    link
    fedilink
    119 days ago

    If you have npm anyway, the npm json package is pretty nice, you can even edit with readable syntax