MCPcopy Create free account

hub / github.com/OpenMOSS/rope_pp / types & classes

Types & classes79 in github.com/OpenMOSS/rope_pp

⨍ Functions 305◇ Types & classes 79↳ Endpoints 5
↓ 10 callersClassCheckpointingCallback
utils/callback_utils.py:72
↓ 10 callersClassCustomLoggingCallback
utils/callback_utils.py:13
↓ 10 callersClassEvaluatingDataset
utils/dataset_utils.py:191
↓ 10 callersClassStreamingTrainingJsonlZSD
utils/dataset_utils.py:17
↓ 10 callersClassTrainerWithDatasetCheckpointing
utils/trainer_utils.py:14
↓ 4 callersClassLlamaModel
Transformer decoder consisting of *config.num_hidden_layers* layers. Each layer is a [`LlamaDecoderLayer`] Args: config: LlamaConfig
rope_pp/modeling_llama_pythia.py:470
↓ 4 callersClassLlamaModel
Transformer decoder consisting of *config.num_hidden_layers* layers. Each layer is a [`LlamaDecoderLayer`] Args: config: LlamaConfig
rope_pp/modeling_llama_alibi.py:587
↓ 4 callersClassLlamaModel
Transformer decoder consisting of *config.num_hidden_layers* layers. Each layer is a [`LlamaDecoderLayer`] Args: config: LlamaConfig
rope_pp/modeling_llama_fope.py:1242
↓ 4 callersClassLlamaModel
Transformer decoder consisting of *config.num_hidden_layers* layers. Each layer is a [`LlamaDecoderLayer`] Args: config: LlamaConfig
rope_pp/modeling_llama_mask.py:502
↓ 4 callersClassLlamaModel
Transformer decoder consisting of *config.num_hidden_layers* layers. Each layer is a [`LlamaDecoderLayer`] Args: config: LlamaConfig
rope_pp/modeling_llama_rope_pp.py:503
↓ 3 callersClassLlamaRMSNorm
rope_pp/modeling_llama_pythia.py:69
↓ 3 callersClassLlamaRMSNorm
rope_pp/modeling_llama_alibi.py:71
↓ 3 callersClassLlamaRMSNorm
rope_pp/modeling_llama_fope.py:55
↓ 3 callersClassLlamaRMSNorm
rope_pp/modeling_llama_mask.py:54
↓ 3 callersClassLlamaRMSNorm
rope_pp/modeling_llama_rope_pp.py:54
↓ 2 callersClassLlamaForCausalLM
rope_pp/modeling_llama_fope.py:1514
↓ 1 callersClassFourierEmbedding
rope_pp/modeling_llama_fope.py:567
↓ 1 callersClassLlamaAttention
Multi-headed attention from 'Attention Is All You Need' paper
rope_pp/modeling_llama_pythia.py:222
↓ 1 callersClassLlamaAttention
rope_pp/modeling_llama_alibi.py:313
↓ 1 callersClassLlamaAttention
Multi-headed attention from 'Attention Is All You Need' paper
rope_pp/modeling_llama_fope.py:904
↓ 1 callersClassLlamaAttention
Multi-headed attention from 'Attention Is All You Need' paper
rope_pp/modeling_llama_mask.py:184
↓ 1 callersClassLlamaAttention
Multi-headed attention from 'Attention Is All You Need' paper
rope_pp/modeling_llama_rope_pp.py:192
↓ 1 callersClassLlamaDecoderLayer
rope_pp/modeling_llama_pythia.py:298
↓ 1 callersClassLlamaDecoderLayer
rope_pp/modeling_llama_alibi.py:415
↓ 1 callersClassLlamaDecoderLayer
rope_pp/modeling_llama_fope.py:1070
↓ 1 callersClassLlamaDecoderLayer
rope_pp/modeling_llama_mask.py:330
↓ 1 callersClassLlamaDecoderLayer
rope_pp/modeling_llama_rope_pp.py:331
↓ 1 callersClassLlamaForCausalLM
rope_pp/modeling_llama_pythia.py:741
↓ 1 callersClassLlamaForCausalLM
rope_pp/modeling_llama_rope_pp.py:774
↓ 1 callersClassLlamaMLP
rope_pp/modeling_llama_pythia.py:168
↓ 1 callersClassLlamaMLP
rope_pp/modeling_llama_alibi.py:162
↓ 1 callersClassLlamaMLP
rope_pp/modeling_llama_fope.py:850
↓ 1 callersClassLlamaMLP
rope_pp/modeling_llama_mask.py:130
↓ 1 callersClassLlamaMLP
rope_pp/modeling_llama_rope_pp.py:138
↓ 1 callersClassLlamaRotaryEmbedding
rope_pp/modeling_llama_pythia.py:92
↓ 1 callersClassLlamaRotaryEmbedding
rope_pp/modeling_llama_alibi.py:94
↓ 1 callersClassLlamaRotaryEmbedding
rope_pp/modeling_llama_fope.py:158
↓ 1 callersClassLlamaRotaryEmbedding
rope_pp/modeling_llama_mask.py:77
↓ 1 callersClassLlamaRotaryEmbedding
rope_pp/modeling_llama_rope_pp.py:77
↓ 1 callersClassMultiTokenEOSCriteria
Criteria to stop on the specified multi-token sequence.
rope_pp/pythia_wrapper.py:24
↓ 1 callersClassMultiTokenEOSCriteria
Criteria to stop on the specified multi-token sequence.
rope_pp/mask_wrapper.py:24
↓ 1 callersClassMultiTokenEOSCriteria
Criteria to stop on the specified multi-token sequence.
rope_pp/rope_pp_wrapper.py:24
↓ 1 callersClassMultiTokenEOSCriteria
Criteria to stop on the specified multi-token sequence.
rope_pp/alibi_wrapper.py:24
↓ 1 callersClassMultiTokenEOSCriteria
Criteria to stop on the specified multi-token sequence.
rope_pp/fope_wrapper.py:24
↓ 1 callersClassRotaryEmbedding
[Rotary positional embeddings (RoPE)](https://arxiv.org/abs/2104.09864).
rope_pp/modeling_llama_fope.py:197
ClassAlibiCausalLM
rope_pp/alibi_wrapper.py:98
ClassFoPECausalLM
rope_pp/fope_wrapper.py:98
ClassKwargsForCausalLM
rope_pp/modeling_llama_pythia.py:738
ClassKwargsForCausalLM
rope_pp/modeling_llama_alibi.py:855
ClassKwargsForCausalLM
rope_pp/modeling_llama_fope.py:1511
ClassKwargsForCausalLM
rope_pp/modeling_llama_mask.py:770
ClassKwargsForCausalLM
rope_pp/modeling_llama_rope_pp.py:771
ClassLlamaConfig
r""" This is the configuration class to store the configuration of a [`LlamaModel`]. It is used to instantiate an LLaMA model according to the
rope_pp/configuration_llama.py:7
ClassLlamaForCausalLM
rope_pp/modeling_llama_alibi.py:858
ClassLlamaForCausalLM
rope_pp/modeling_llama_mask.py:773
ClassLlamaForQuestionAnswering
rope_pp/modeling_llama_pythia.py:972
ClassLlamaForQuestionAnswering
rope_pp/modeling_llama_alibi.py:1089
ClassLlamaForQuestionAnswering
rope_pp/modeling_llama_fope.py:1743
ClassLlamaForQuestionAnswering
rope_pp/modeling_llama_mask.py:1002
ClassLlamaForQuestionAnswering
rope_pp/modeling_llama_rope_pp.py:1003
ClassLlamaForSequenceClassification
rope_pp/modeling_llama_pythia.py:879
ClassLlamaForSequenceClassification
rope_pp/modeling_llama_alibi.py:996
ClassLlamaForSequenceClassification
rope_pp/modeling_llama_fope.py:1650
ClassLlamaForSequenceClassification
rope_pp/modeling_llama_mask.py:909
ClassLlamaForSequenceClassification
rope_pp/modeling_llama_rope_pp.py:910
ClassLlamaForTokenClassification
rope_pp/modeling_llama_pythia.py:1053
ClassLlamaForTokenClassification
rope_pp/modeling_llama_alibi.py:1170
ClassLlamaForTokenClassification
rope_pp/modeling_llama_fope.py:1824
ClassLlamaForTokenClassification
rope_pp/modeling_llama_mask.py:1083
ClassLlamaForTokenClassification
rope_pp/modeling_llama_rope_pp.py:1084
ClassLlamaPreTrainedModel
rope_pp/modeling_llama_pythia.py:373
ClassLlamaPreTrainedModel
rope_pp/modeling_llama_alibi.py:490
ClassLlamaPreTrainedModel
rope_pp/modeling_llama_fope.py:1145
ClassLlamaPreTrainedModel
rope_pp/modeling_llama_mask.py:405
ClassLlamaPreTrainedModel
rope_pp/modeling_llama_rope_pp.py:406
ClassMaskCausalLM
rope_pp/mask_wrapper.py:98
ClassPythiaCausalLM
rope_pp/pythia_wrapper.py:98
ClassRoPEPPCausalLM
rope_pp/rope_pp_wrapper.py:98
ClassStreamingTrainingParquet
utils/dataset_utils.py:104