Results
5
comments of
Javier Martínez
trafficstars
+1 interested in fine tunning prompt encoder or mask decoder!
Hi! @amyeroberts, any news on this one? :) Thanks!
hi @younesbelkada! The issue is marked as stale, hos it it going? :) thanks!
Ok thanks! BTW, I suppose that if with LoRA I avoid targetting LM head but still target embeddings, after the merge_and_unload() the LM head will get mutated again resulting in...