Custom-Transformer-Pytorch
PublicA clean, ground-up implementation of the Transformer architecture in PyTorch, including positional encoding, multi-head attention, encoder-decoder layers, and masking. Great for learning or building upon the core model.
attention-mechanismdeep-learningencoder-decodermachine-learningnlppositional-encodingpytorchself-attentionsequence-to-sequencetransformers
创建时间：2025-05-22T13:29:43
更新时间：2025-11-24T16:01:09
16
Stars
0
Stars Increase