Fine tune of Multi-news dataset

yizhongw / Tk-Instruct

Tk-Instruct is a Transformer model that is tuned to solve many NLP tasks by following instructions.

https://arxiv.org/abs/2204.07705

MIT License

177 stars 27 forks source link

Fine tune of Multi-news dataset #15

Open Ronica1234 opened 1 year ago

Ronica1234 commented 1 year ago

Hello,

Could we finetune (few shot e.g. 200 steps) or prompt tune (e.g. soft prompt tuning) the model on specific dataset. , do you have any code for these tasks. Thanks

SaraAmd commented 1 year ago

Can we use this model for regression?

SaraAmd commented 1 year ago

@Ronica1234 Did you find any answer to your question? I also want to know if we can fine-tune ir or not and if yes how?