transformers

9907265b - refactor: use DecoderLayer pattern; drop moe_latent_size; inherit MixtralExperts

refactor: use DecoderLayer pattern; drop moe_latent_size; inherit MixtralExperts - Replace Block/mixer abstraction with NemotronH{Dense,Sparse}DecoderLayer holding exactly one of self.mamba / self.self_attn / self.mlp|block_sparse_moe based on layer_type, matching the standard decoder-layer pattern. - Pass attention_mask (4D causal) + mamba_attention_mask (raw 2D) uniformly to every layer instead of pre-dispatching per layer type. - NemotronHSparseExperts now inherits from MixtralExperts (non-gated variant). - Drop moe_latent_size from sparse config and the matching latent projections — the field is not present in the released Nemotron-3 config.