Fine-tuning this model

#1
by danielus - opened

Hi! I want to approach the world of language models a little more seriously, so I would like to try finetuning a model. Not experience with this, would you be able to tell me if this model is finetunable further? Or since you have already done your finetuning I might have poor results?

I would like to try finetuning it on a specific task and I have a few hundred prompt-response examples.

Hi! Absolutely, you can further finetune this model for a specific task. I am actually updating the model in a few hours to enhance its understanding of Italian, logical reasoning, and critical thinking. Finetuning on your specific task with a few hundred prompt-response examples should yield decent results, especially after the upcoming updates. Let me know if you need any assistance with the finetuning process!

I will look forward to the update. Thank you very much <3

Regarding training, I currently have a laptop with a rtx 2060 6GB of VRAM, but according to the huggingface space Can-You-Run-It's not enough to train it in fp16, does training it with lower accuracies worsen the quality of training?

I could potentially use a VM on google cloud with a Nvidia L4, how long more or less does it take to finetuning?

Doing rough calculations each prompt-response pair is about 2k tokens, so if I were to have about 300 examples that's 600k tokens

I would prefer to train it on my laptop, since I can take my time and experiment more comfortably. What do you think?

Sign up or log in to comment