Uses of Package
ai.beestream.jitnn.nn

Packages that use ai.beestream.jitnn.nn
Package
Description
Neural-network modules after PyTorch's torch.nn: Module and Sequential, linear and convolution layers, pooling, normalisation, attention, embeddings, recurrent layers (LSTM, GRU), graph convolution, activations, and data-parallel training (DataParallel).
Complete models: ResNet, MobileNetV2, GPT-2, a Llama-style decoder, BERT, a VAE, DCGAN, U-Net and character RNNs, and the embedding models word2vec, doc2vec and GloVe.
  • Class
    Description
    Data-parallel training with one model replica per rank (see ProcessGroup): broadcast rank 0's parameters once, then after each backward pass average the gradients over the ranks before the optimiser step, so every replica takes the same step, as PyTorch's DistributedDataParallel does.
    Graph convolution (Kipf and Welling, 2017), PyTorch Geometric's GCNConv:  (x W^T) + b, with  the normalised adjacency SparseMatrix.gcn(int, int[], int[]) of the graph, given with each call since one layer serves many graphs. x [nodes, in] gives [nodes, out].
    Output sequence of the last layer [T, B, directions H] and the final hidden states, [layers directions, B, H] each.
    y = x W^T + b with W of shape [out, in].
    Output sequence of the last layer [T, B, directions H] and the final hidden states and cell states, [layers directions, B, H] each.
    A differentiable building block with parameters and child modules.
  • Class
    Description
    A differentiable building block with parameters and child modules.
    Applies its modules in order.