All modules for which code is available
- src.cli
- src.deploy.deploy
- src.deploy.inference
- src.deploy.quantization
- src.model.activation_function.common
- src.model.activation_function.exponential
- src.model.activation_function.factory
- src.model.activation_function.glu
- src.model.activation_function.learnable
- src.model.activation_function.rectified
- src.model.attention.common
- src.model.attention.engram
- src.model.attention.gated.deltanet_attn
- src.model.attention.gated.fox_attn
- src.model.attention.gated.gated_deltanet2_attn
- src.model.attention.gated.gated_deltanet_attn
- src.model.attention.gated.gated_softmax_attn
- src.model.attention.gated.gla_attn
- src.model.attention.gated.hgrn2_attn
- src.model.attention.gated.kda_attn
- src.model.attention.gated.retnet_attn
- src.model.attention.grouped_query_attention
- src.model.attention.latent.cca_attn
- src.model.attention.latent.gqla_attn
- src.model.attention.latent.gta_attn
- src.model.attention.latent.iha_attn
- src.model.attention.latent.mla_attn
- src.model.attention.latent.mlra_attn
- src.model.attention.latent.mtla_attn
- src.model.attention.latent.tucker_attn
- src.model.attention.ode
- src.model.attention.retnet
- src.model.attention.sigmoid
- src.model.attention.sparse.bigbird_attn
- src.model.attention.sparse.fasa_attn
- src.model.attention.sparse.longformer_attn
- src.model.attention.sparse.msa_attn
- src.model.attention.sparse.nsa_attn
- src.model.attention.sparse.sparda_attn
- src.model.attention.sparse.sparge_attn
- src.model.attention.sparse.sparse_transformer_attn
- src.model.attention.sparse.sparsek_attn
- src.model.attention.standard
- src.model.attention.titan
- src.model.embeddings.factorized_embedding
- src.model.embeddings.hope
- src.model.embeddings.rope
- src.model.norm.derf
- src.model.norm.dynamic_tanh
- src.model.norm.factory
- src.model.norm.rms
- src.model.optimizer.adamw
- src.model.optimizer.adan
- src.model.optimizer.ademamix
- src.model.optimizer.adopt
- src.model.optimizer.apollo
- src.model.optimizer.apollo_mini
- src.model.optimizer.cautious_adamw
- src.sbert.inference_sbert
- src.tokenizer.spm_spa_redpajama35
- src.training.streaming_mlm_dataset
- src.utils.device
- src.utils.gpu_temp_guard
- src.utils.storage_manager
- torch