ScholarGate
Assistente

Confronta i metodi

Esamina i metodi selezionati fianco a fianco; le righe che differiscono sono evidenziate.

Ottimizzazione Diretta delle Preferenze×QLoRA×
CampoApprendimento profondoApprendimento profondo
FamigliaMachine learningMachine learning
Anno di origine20232023
IdeatoreRafael RafailovTim Dettmers
TipoTraining methodologyTraining methodology
Fonte seminaleRafailov, 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 ↗
AliasDPO, Direct preferenceQLoRA, Quantized LoRA
Correlati44
SintesiDirect 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.
ScholarGateInsieme di dati
  1. v1
  2. 1 Fonti
  3. PUBLISHED
  1. v1
  2. 1 Fonti
  3. PUBLISHED

Vai alla ricerca Scarica le diapositive

ScholarGateConfronta i metodi: Direct Preference Optimization · QLoRA. Consultato il 2026-06-15 da https://scholargate.app/it/compare