ScholarGate
Асистент

Порівняння методів

Переглядайте обрані методи поруч; рядки з відмінностями підсвічено.

QLoRA×Пряма оптимізація вподобань×Масковані автокодувальники×
ГалузьГлибоке навчанняГлибоке навчанняГлибоке навчання
РодинаMachine learningMachine learningMachine learning
Рік появи202320232021
Автор методуTim DettmersRafael RafailovKaiming He
ТипTraining methodologyTraining methodologyNeural network architecture
Основоположне джерелоDettmers, T., Pagnoni, A., Holtzman, A., & Contrastive, L. (2023). QLoRA: Efficient finetuning of quantized LLMs. arXiv preprint arXiv:2305.14314. link ↗Rafailov, 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 ↗
Інші назвиQLoRA, Quantized LoRADPO, Direct preferenceMAE, Vision MAE
Пов'язані444
ПідсумокQLoRA 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.Direct 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.
ScholarGateНабір даних
  1. v1
  2. 1 Джерела
  3. PUBLISHED
  1. v1
  2. 1 Джерела
  3. PUBLISHED
  1. v1
  2. 1 Джерела
  3. PUBLISHED

Перейти до пошуку Завантажити слайди

ScholarGateПорівняння методів: QLoRA · Direct Preference Optimization · Masked Autoencoders. Отримано 2026-06-18 з https://scholargate.app/uk/compare