google
/

gemma-3-4b-it

Image-Text-to-Text

text-generation-inference

Model card Files Files and versions

Having a hard time fine tuning with LoRA

#21

by abcampbell - opened Mar 16

Mar 16

Spent 4 hrs and lots of conflicts btw transformers, sft and other pakcages the tuner needs, has anyone got a fine tuned version running?

Mar 18

I spent 5 hours trying to figure out today but I found this source and I think it works (we'll see I am running the script right now): https://ai.google.dev/gemma/docs/core/huggingface_text_finetune_qlora

Google org Mar 19

Hi @abcampbell ,

Could you please check this link for fine-tuning details.

Thank you.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment