fine tuning
#2
by
arshiaafshani
- opened
hi
how can I fine tune this model? and also is there any way to change it's algorithms?
Hi,
You need to use the TRL library to fine-tune it because it requires several memory optimization methods to use them on Colab and T4 GPUs.
For the second question, I don't understand what you mean about changing the algorithm.
I meant changing the process of generating a prompt, the codes that contain the generation a result. Can I have your Telegram username?
Yes you can do that. You change prompt style or you can use your own way
Thanks !