Archives

Recurrent Neural Networks: 用隐藏状态处理序列

Transformer - 从 Additive Attention 到 Multi-Head Attention

LoRA的学习率 LoRA+: Efficient Low Rank Adaptation

LoRA的秩与容量 AdaLoRA: Adaptive Budget Allocation

LoRA的显存成本 QLoRA: Efficient Finetuning of Quantized LLMs

LoRA: Low-Rank Adaptation

Before LoRA 2: Sparse Projection, Fastfood, and SAID

Before LoRA: Measuring the Intrinsic Dimension

Transformer - Transformer Decoder

深度学习中的权重初始化

Transformer - Transformer Encoder

Transformer - Transformer 的输入嵌入与位置编码

Batch Normalization 与 Layer Normalization

TrainingSkills

Autoencoder

DenoisingAutoencoder

Lagrangian Optimization

SVM