search

naver / splade

SPLADE: sparse neural search (SIGIR21, SIGIR22)
Other
751 stars 84 forks source link

Fine Tuning #20

Closed shaileshj2803 closed 2 years ago

shaileshj2803 commented 2 years ago

Do you have example of finetuning?

thibault-formal commented 2 years ago

Hi @shaileshj2803 ,

What do you mean exactly? Training SPLADE can be seen as "finetuning" (we start from a pre-trained BERT); you have all the steps described in the README.

If you are looking for actual examples of SPLADE outputs, you can have a look at inference_splade.ipynb

Thibault

thibault-formal commented 2 years ago

Let us know if you need more details, in the meantime I close the issue.

Thibault

shaileshj2803 commented 2 years ago

Sure thanks