nvFP4 script

#1
by vgoklani - opened

Thanks for posting the model. Could you please share your exact conversion script. I'd like to convert llama4-scout using nvFP4, thanks!

I have shared it over on this comment thread here:
https://huggingface.co/Firworks/MiroThinker-v1.0-30B-nvfp4/discussions/1#69269c6d40ce1d3b1a6ca1cc

The only thing I've updated since then is excluding out some patterns for vision elements to support multimodal models:

    ignore=[
        "lm_head",
        "re:visual.*",                 # everything under the `visual` tower
        "re:.*vision_tower.*",         # common naming in other VL models
        "re:.*video_tower.*",          # in case the checkpoint has video tower
        "re:.*audio_tower.*",          # if there’s an audio tower
        "re:.*multi_modal_projector.*" # bridge projector, if present
    ],

Sign up or log in to comment