热点
"LayerNorm" 相关文章
一文讲清 nn.LayerNorm ​层归一化
掘金 人工智能 2025-09-16T03:13:41.000000Z
一文讲清 nn.LayerNorm ​层归一化
掘金 人工智能 2025-09-16T03:13:41.000000Z
Positional embeddings in GPT-2 lie near(ish) the surface of a hypersphere
少点错误 2025-09-11T00:50:52.000000Z
Minor interpretability exploration #4: LayerNorm and the learning coefficient
少点错误 2025-03-21T02:05:09.000000Z
You can remove GPT2’s LayerNorm by fine-tuning for an hour
少点错误 2024-08-08T18:36:43.000000Z