ScholarGate
Асистент

Сравнение на методи

Прегледайте избраните методи един до друг; редовете с разлики са откроени.

Директна оптимизация на предпочитанията×Маскирани автоенкодери×QLoRA×
ОбластДълбоко обучениеДълбоко обучениеДълбоко обучение
СемействоMachine learningMachine learningMachine learning
Година на възникване202320212023
СъздателRafael RafailovKaiming HeTim Dettmers
ТипTraining methodologyNeural network architectureTraining methodology
Основополагащ източникRafailov, R., Sharma, A., Mitchell, E., Manning, C. D., Ermon, S., & Finn, C. (2023). Direct preference optimization: Your language model is secretly a reward model. arXiv preprint arXiv:2305.18290. link ↗He, 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 ↗
Други названияDPO, Direct preferenceMAE, Vision MAEQLoRA, Quantized LoRA
Свързани444
РезюмеDirect Preference Optimization (DPO) is a training method introduced by Rafailov et al. in 2023 that aligns language models with human preferences without requiring an explicit reward model. By directly optimizing for preference pairs (better response vs worse response), DPO simplifies the training pipeline compared to reinforcement learning from human feedback (RLHF).Masked 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.
ScholarGateНабор от данни
  1. v1
  2. 1 Източници
  3. PUBLISHED
  1. v1
  2. 1 Източници
  3. PUBLISHED
  1. v1
  2. 1 Източници
  3. PUBLISHED

Към търсенето Изтегляне на слайдове

ScholarGateСравнение на методи: Direct Preference Optimization · Masked Autoencoders · QLoRA. Извлечено на 2026-06-18 от https://scholargate.app/bg/compare