微信扫码
添加专属顾问
我要投稿
LISA 算法的核心在于:
- 始终更新底层 embedding 和顶层 linear head;
一键使用LISA
总结
参考文献
[1] Hu, Edward J., et al. "Lora: Low-rank adaptation of large language models." ICLR 2022.
[2] Dettmers, Tim, et al. "Qlora: Efficient finetuning of quantized llms." Advances in Neural Information Processing Systems 36 (2024).
[3] Ding, Ning, et al. "Delta tuning: A comprehensive study of parameter efficient methods for pre-trained language models." arXiv preprint arXiv:2203.06904 (2022).
[4] Lialin, Vladislav, et al. "Stack more layers differently: High-rank training through low-rank updates." arXiv preprint arXiv:2307.05695 (2023).
53AI,企业落地大模型首选服务商
产品:场景落地咨询+大模型应用平台+行业解决方案
承诺:免费场景POC验证,效果验证后签署服务协议。零风险落地应用大模型,已交付160+中大型企业
2025-02-01
2024-07-25
2025-01-01
2025-02-04
2024-08-13
2024-04-25
2024-06-13
2024-08-21
2024-09-23
2024-04-26
2025-04-24
2025-04-24
2025-04-23
2025-04-23
2025-04-23
2025-04-22
2025-04-22
2025-04-22