MCPcopy Create free account

hub / github.com/WailordHe/DenseSSM / types & classes

Types & classes24 in github.com/WailordHe/DenseSSM

⨍ Functions 107◇ Types & classes 24↳ Endpoints 2
↓ 5 callersClassLlamaRMSNorm
modeling/dense_gau_retnet_1p3b/modeling_dense_gau_retnet.py:75
↓ 5 callersClassLlamaRMSNorm
modeling/dense_gau_retnet_350m/modeling_dense_gau_retnet.py:75
↓ 2 callersClassDenseGAURetNetModel
Transformer decoder consisting of *config.num_hidden_layers* layers. Each layer is a [`LlamaDecoderLayer`] Args: config: LlamaConfig
modeling/dense_gau_retnet_1p3b/modeling_dense_gau_retnet.py:456
↓ 2 callersClassDenseGAURetNetModel
Transformer decoder consisting of *config.num_hidden_layers* layers. Each layer is a [`LlamaDecoderLayer`] Args: config: LlamaConfig
modeling/dense_gau_retnet_350m/modeling_dense_gau_retnet.py:456
↓ 2 callersClassHiddenProjection
modeling/dense_gau_retnet_1p3b/modeling_dense_gau_retnet.py:103
↓ 2 callersClassHiddenProjection
modeling/dense_gau_retnet_350m/modeling_dense_gau_retnet.py:103
↓ 1 callersClassLlamaDecoderLayer
modeling/dense_gau_retnet_1p3b/modeling_dense_gau_retnet.py:267
↓ 1 callersClassLlamaDecoderLayer
modeling/dense_gau_retnet_350m/modeling_dense_gau_retnet.py:267
↓ 1 callersClassMultiScaleGauRetention
Multi-headed attention from 'Attention Is All You Need' paper
modeling/dense_gau_retnet_1p3b/modeling_dense_gau_retnet.py:116
↓ 1 callersClassMultiScaleGauRetention
Multi-headed attention from 'Attention Is All You Need' paper
modeling/dense_gau_retnet_350m/modeling_dense_gau_retnet.py:116
↓ 1 callersClassRetNetRelPos
modeling/dense_gau_retnet_1p3b/modeling_dense_gau_retnet.py:424
↓ 1 callersClassRetNetRelPos
modeling/dense_gau_retnet_350m/modeling_dense_gau_retnet.py:424
ClassDataArguments
train.py:64
ClassLlamaForCausalLM
modeling/dense_gau_retnet_1p3b/modeling_dense_gau_retnet.py:685
ClassLlamaForCausalLM
modeling/dense_gau_retnet_350m/modeling_dense_gau_retnet.py:685
ClassLlamaForSequenceClassification
modeling/dense_gau_retnet_1p3b/modeling_dense_gau_retnet.py:905
ClassLlamaForSequenceClassification
modeling/dense_gau_retnet_350m/modeling_dense_gau_retnet.py:905
ClassLlamaPreTrainedModel
modeling/dense_gau_retnet_1p3b/modeling_dense_gau_retnet.py:336
ClassLlamaPreTrainedModel
modeling/dense_gau_retnet_350m/modeling_dense_gau_retnet.py:336
ClassModelArguments
train.py:59
ClassPretrainArguments
train.py:212
ClassPretrainDataArguments
Arguments pertaining to what data we are going to input our model for training and eval.
train.py:143
ClassPretrainModelArguments
Arguments pertaining to which model/config/tokenizer we are going to fine-tune, or train from scratch.
train.py:82
ClassTrainingArguments
train.py:69