Leshem Choshen · @LChoshen
753 followers · 95 posts · Server sigmoid.social

We want to pretrain🤞
Instead we finetune🚮😔
Could we collaborate?🤗

ColD Fusion:
🔄Recycle finetuning to multitask
➡️evolve pretrained models forever

On 35 datasets
+2% improvement over RoBERTa
+7% in few shot settings
🧵

#nlproc #machinlearning #nlp #ml #modelrecyclying #CollaborativeAI #scientivism #pretrain

Last updated 3 years ago

Leshem Choshen · @LChoshen
753 followers · 94 posts · Server sigmoid.social

We want to pretrain🤞
Instead we finetune🚮😔
Could we collaborate?🤗

ColD Fusion:
🔄Recycle finetuning to multitask
➡️evolve pretrained models forever

On 35 datasets
+2% improvement over RoBERTa
+7% in few shot settings
🧵

#nlproc #machinlearning #nlp #ml #modelrecyclying

Last updated 3 years ago