热点
"指令调优" 相关文章
Enhancing Instruction Tuning in LLMs: A Diversity-Aware Data Selection Strategy Using Sparse Autoencoders
MarkTechPost@AI 2025-02-25T17:48:40.000000Z
颠覆LLM格局！AI2新模型OLMo2，训练过程全公开，数据架构双升级
新智元 2025-01-25T17:07:25.000000Z
代码模型自我进化超越GPT-4o蒸馏！UIUC伯克利等提出自对齐方法 | NIPS 2024
新智元 2024-11-29T08:00:40.000000Z
SQ-LLaVA: A New Visual Instruction Tuning Method that Enhances General-Purpose Vision-Language Understanding and Image-Oriented Question Answering through Visual Self-Questioning
MarkTechPost@AI 2024-10-10T12:36:22.000000Z
Instructive Decoding (ID): A Novel AI Method that Enhances the Attention of Instruction-Tuned LLMs Towards Provided Instructions during the Generation Phase without Any Parameter Updates
MarkTechPost@AI 2024-10-02T07:21:18.000000Z
Falcon Mamba: 首个高效的无注意力机制 7B 模型
智源社区 2024-09-06T04:22:39.000000Z
大模型指令调优数据集万字评测！腾讯上交大联合出品
智源社区 2024-08-19T04:22:42.000000Z