Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Mundra, Nandini"'
Autor:
Mundra, Nandini, Kishore, Aditya Nanda, Dabre, Raj, Puduppully, Ratish, Kunchukuttan, Anoop, Khapra, Mitesh M.
Language Models (LMs) excel in natural language processing tasks for English but show reduced performance in most other languages. This problem is commonly tackled by continually pre-training and fine-tuning these models for said languages. A signifi
Externí odkaz:
http://arxiv.org/abs/2407.05841
Autor:
Mundra, Nandini, Doddapaneni, Sumanth, Dabre, Raj, Kunchukuttan, Anoop, Puduppully, Ratish, Khapra, Mitesh M.
Adapters have been positioned as a parameter-efficient fine-tuning (PEFT) approach, whereby a minimal number of parameters are added to the model and fine-tuned. However, adapters have not been sufficiently analyzed to understand if PEFT translates t
Externí odkaz:
http://arxiv.org/abs/2305.07491