Compară metode
Examinează metodele selectate una lângă alta; rândurile care diferă sunt evidențiate.
| Optimizarea Directă a Preferințelor× | Modele de difuzie latente× | QLoRA× | |
|---|---|---|---|
| Domeniu | Învățare profundă | Învățare profundă | Învățare profundă |
| Familie | Machine learning | Machine learning | Machine learning |
| Anul apariției≠ | 2023 | 2022 | 2023 |
| Autorul original≠ | Rafael Rafailov | Robin Rombach | Tim Dettmers |
| Tip≠ | Training methodology | Neural network architecture | Training methodology |
| Sursa seminală≠ | 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 ↗ | Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 10684-10695). DOI ↗ | Dettmers, T., Pagnoni, A., Holtzman, A., & Contrastive, L. (2023). QLoRA: Efficient finetuning of quantized LLMs. arXiv preprint arXiv:2305.14314. link ↗ |
| Denumiri alternative≠ | DPO, Direct preference | LDM, Stable Diffusion, Latent Diffusion | QLoRA, Quantized LoRA |
| Înrudite | 4 | 4 | 4 |
| Rezumat≠ | 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). | Latent Diffusion Models (LDMs) are a generative approach introduced by Rombach et al. in 2022 that performs the diffusion process in a compressed latent space rather than pixel space, enabling efficient high-resolution image synthesis. By compressing images into a low-dimensional latent representation using a variational autoencoder, diffusion becomes computationally tractable while maintaining visual quality. | 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. |
| ScholarGateSet de date ↗ |
|
|
|