Võrdle meetodeid
Vaata valitud meetodeid kõrvuti; erinevad read on esile tõstetud.
| QLoRA× | Mamba (oleku-ruumi mudel)× | |
|---|---|---|
| Valdkond | Süvaõpe | Süvaõpe |
| Perekond | Machine learning | Machine learning |
| Tekkeaasta | 2023 | 2023 |
| Looja≠ | Tim Dettmers | Albert Gu |
| Tüüp≠ | Training methodology | Neural network architecture |
| Algallikas≠ | Dettmers, T., Pagnoni, A., Holtzman, A., & Contrastive, L. (2023). QLoRA: Efficient finetuning of quantized LLMs. arXiv preprint arXiv:2305.14314. link ↗ | Gu, A., & Dao, C. (2023). Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.08956. link ↗ |
| Rööpnimetused≠ | QLoRA, Quantized LoRA | Mamba, State space models, Selective state space |
| Seotud | 4 | 4 |
| Kokkuvõte≠ | 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. | Mamba is a sequence model architecture introduced by Gu and Dao in 2023 that achieves linear-time complexity while maintaining strong performance on language modeling tasks. By combining state space models with input-dependent selectivity, Mamba addresses the quadratic complexity of transformers while preserving modeling power. |
| ScholarGateAndmestik ↗ |
|
|