head

Auto-generated from flax_nnx_code_defs

PyTorchFlax NNX

PyTorch

API: torch.nn.modules.adaptive.AdaptiveLogSoftmaxWithLoss.head

Strategy: Direct Mapping

Official Docs ↗

Flax NNX

API: nnx.nn.attention.MultiHeadAttention.head_dim

Strategy: Direct Mapping

Official Docs ↗