ScholarGate
المساعد

قارن الطرق

راجع الطرق التي اخترتها جنبًا إلى جنب؛ الصفوف المختلفة مميَّزة.

التحسين المباشر للتفضيلات×كيولورا×
المجالالتعلم العميقالتعلم العميق
العائلةMachine learningMachine learning
سنة النشأة20232023
صاحب الطريقةRafael RafailovTim Dettmers
النوعTraining methodologyTraining methodology
المصدر التأسيسيRafailov, 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 ↗Dettmers, T., Pagnoni, A., Holtzman, A., & Contrastive, L. (2023). QLoRA: Efficient finetuning of quantized LLMs. arXiv preprint arXiv:2305.14314. link ↗
الأسماء البديلةDPO, Direct preferenceQLoRA, Quantized LoRA
ذات صلة44
الملخصDirect 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).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.
ScholarGateمجموعة البيانات
  1. v1
  2. 1 المصادر
  3. PUBLISHED
  1. v1
  2. 1 المصادر
  3. PUBLISHED

انتقل إلى البحث تنزيل الشرائح

ScholarGateقارن الطرق: Direct Preference Optimization · QLoRA. استُرجع بتاريخ 2026-06-15 من https://scholargate.app/ar/compare