ScholarGate
Asistents

Salīdzināt metodes

Apskatiet izvēlētās metodes blakus; rindas, kas atšķiras, ir izceltas.

Apslēptie autoenkoderi×QLoRA×
NozareDziļā mācīšanāsDziļā mācīšanās
SaimeMachine learningMachine learning
Izcelsmes gads20212023
AutorsKaiming HeTim Dettmers
TipsNeural network architectureTraining methodology
PirmavotsHe, K., Chen, X., Xie, S., Li, Y., Dollár, P., & Girshick, R. (2022). Masked autoencoders are scalable vision learners. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 16000-16009). DOI ↗Dettmers, T., Pagnoni, A., Holtzman, A., & Contrastive, L. (2023). QLoRA: Efficient finetuning of quantized LLMs. arXiv preprint arXiv:2305.14314. link ↗
Citi nosaukumiMAE, Vision MAEQLoRA, Quantized LoRA
Saistītās44
KopsavilkumsMasked Autoencoders (MAE) is a self-supervised learning approach introduced by He et al. in 2021 that masks random patches of an image and trains a model to reconstruct the missing content. Adapting the masked language modeling paradigm from NLP to vision, MAE learns rich visual representations by solving a challenging reconstruction task without requiring labels.QLoRA is an efficient fine-tuning method introduced by Dettmers et al. in 2023 that enables fine-tuning large language models using quantization and low-rank adaptation. By combining 4-bit quantization with LoRA, QLoRA reduces memory requirements by 75%, enabling fine-tuning of 65B-parameter models on single GPUs.
ScholarGateDatu kopa
  1. v1
  2. 1 Avoti
  3. PUBLISHED
  1. v1
  2. 1 Avoti
  3. PUBLISHED

Doties uz meklēšanu Lejupielādēt slaidus

ScholarGateSalīdzināt metodes: Masked Autoencoders · QLoRA. Izgūts 2026-06-18 no https://scholargate.app/lv/compare