Porównaj metody
Przeglądaj wybrane metody obok siebie; wiersze, które się różnią, są wyróżnione.
| QLoRA× | Modele dyfuzyjne w przestrzeni utajonej× | |
|---|---|---|
| Dziedzina | Uczenie głębokie | Uczenie głębokie |
| Rodzina | Machine learning | Machine learning |
| Rok powstania≠ | 2023 | 2022 |
| Twórca≠ | Tim Dettmers | Robin Rombach |
| Typ≠ | Training methodology | Neural network architecture |
| Źródło pierwotne≠ | Dettmers, T., Pagnoni, A., Holtzman, A., & Contrastive, L. (2023). QLoRA: Efficient finetuning of quantized LLMs. arXiv preprint arXiv:2305.14314. 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 ↗ |
| Inne nazwy≠ | QLoRA, Quantized LoRA | LDM, Stable Diffusion, Latent Diffusion |
| Pokrewne | 4 | 4 |
| Podsumowanie≠ | 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. | 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. |
| ScholarGateZbiór danych ↗ |
|
|