Skip to main content
Ctrl+K

Megatron-LLM 0.1.0 documentation

  • User guide
  • API
  • User guide
  • API

Section Navigation

  • megatron.arguments
    • megatron.arguments.build_base_parser
    • megatron.arguments.parse_args
    • megatron.arguments.validate_args
  • megatron.checkpointing
    • megatron.checkpointing.check_checkpoint_args
    • megatron.checkpointing.ensure_directory_exists
    • megatron.checkpointing.find_checkpoint_rank_0
    • megatron.checkpointing.fix_query_key_value_ordering
    • megatron.checkpointing.get_checkpoint_name
    • megatron.checkpointing.get_checkpoint_names
    • megatron.checkpointing.get_checkpoint_tracker_filename
    • megatron.checkpointing.get_checkpoint_version
    • megatron.checkpointing.get_rng_state
    • megatron.checkpointing.load_args_from_checkpoint
    • megatron.checkpointing.load_biencoder_checkpoint
    • megatron.checkpointing.load_checkpoint
    • megatron.checkpointing.read_metadata
    • megatron.checkpointing.save_checkpoint
    • megatron.checkpointing.set_checkpoint_version
  • megatron.dist_signal_handler
    • megatron.dist_signal_handler.DistributedSignalHandler
    • megatron.dist_signal_handler.all_gather_item
    • megatron.dist_signal_handler.get_device
    • megatron.dist_signal_handler.get_world_size
  • megatron.global_vars
    • megatron.global_vars.get_adlr_autoresume
    • megatron.global_vars.get_args
    • megatron.global_vars.get_counters
    • megatron.global_vars.get_current_global_batch_size
    • megatron.global_vars.get_num_microbatches
    • megatron.global_vars.get_signal_handler
    • megatron.global_vars.get_tensorboard_writer
    • megatron.global_vars.get_timers
    • megatron.global_vars.get_tokenizer
    • megatron.global_vars.rebuild_tokenizer
    • megatron.global_vars.set_global_variables
    • megatron.global_vars.update_num_microbatches
  • megatron.indexer
    • megatron.indexer.IndexBuilder
  • megatron.initialize
    • megatron.initialize.initialize_megatron
    • megatron.initialize.set_jit_fusion_options
    • megatron.initialize.write_args_to_tensorboard
  • megatron.memory
    • megatron.memory.MemoryBuffer
    • megatron.memory.RingMemBuffer
    • megatron.memory.allocate_mem_buff
    • megatron.memory.get_mem_buff
  • megatron.microbatches
    • megatron.microbatches.ConstantNumMicroBatches
    • megatron.microbatches.NumMicroBatchesCalculator
    • megatron.microbatches.RampupBatchsizeNumMicroBatches
    • megatron.microbatches.build_num_microbatches_calculator
  • megatron.optimizer_param_scheduler
    • megatron.optimizer_param_scheduler.OptimizerParamScheduler
  • megatron.p2p_communication
    • megatron.p2p_communication.recv_backward
    • megatron.p2p_communication.recv_forward
    • megatron.p2p_communication.send_backward
    • megatron.p2p_communication.send_backward_recv_backward
    • megatron.p2p_communication.send_backward_recv_forward
    • megatron.p2p_communication.send_forward
    • megatron.p2p_communication.send_forward_backward_recv_forward_backward
    • megatron.p2p_communication.send_forward_recv_backward
    • megatron.p2p_communication.send_forward_recv_forward
  • megatron.schedules
    • megatron.schedules.backward_step
    • megatron.schedules.custom_backward
    • megatron.schedules.deallocate_output_tensor
    • megatron.schedules.dummy_handler
    • megatron.schedules.forward_backward_no_pipelining
    • megatron.schedules.forward_backward_pipelining_with_interleaving
    • megatron.schedules.forward_backward_pipelining_without_interleaving
    • megatron.schedules.forward_step
    • megatron.schedules.get_forward_backward_func
    • megatron.schedules.get_tensor_shapes
    • megatron.schedules.recv_backward
    • megatron.schedules.recv_forward
    • megatron.schedules.send_backward
    • megatron.schedules.send_backward_recv_forward
    • megatron.schedules.send_forward
    • megatron.schedules.send_forward_recv_backward
  • megatron.text_generation_server
    • megatron.text_generation_server.MegatronGenerate
    • megatron.text_generation_server.MegatronServer
  • megatron.timers
    • megatron.timers.DummyTimer
    • megatron.timers.Timer
    • megatron.timers.TimerBase
    • megatron.timers.Timers
  • megatron.training
    • megatron.training.build_train_valid_test_data_iterators
    • megatron.training.cyclic_iter
    • megatron.training.evaluate
    • megatron.training.evaluate_and_print_results
    • megatron.training.get_model
    • megatron.training.pretrain
    • megatron.training.print_datetime
    • megatron.training.save_checkpoint_and_time
    • megatron.training.train_step
    • megatron.training.training_log
  • megatron.utils
    • megatron.utils.average_losses_across_data_parallel_group
    • megatron.utils.calc_params_l2_norm
    • megatron.utils.check_adlr_autoresume_termination
    • megatron.utils.get_ltor_masks_and_position_ids
    • megatron.utils.is_last_local_rank
    • megatron.utils.is_last_rank
    • megatron.utils.print_all_nodes
    • megatron.utils.print_params_min_max_norm
    • megatron.utils.print_rank_0
    • megatron.utils.print_rank_last
    • megatron.utils.report_memory
    • megatron.utils.unwrap_model
  • megatron.wandb_logger
    • megatron.wandb_logger.WandBConfig
    • megatron.wandb_logger.WandbTBShim
    • megatron.wandb_logger.toy_test
    • megatron.wandb_logger.try_catch_guard
  • megatron.core.parallel_state
    • megatron.core.parallel_state.destroy_model_parallel
    • megatron.core.parallel_state.get_data_parallel_group
    • megatron.core.parallel_state.get_data_parallel_rank
    • megatron.core.parallel_state.get_data_parallel_src_rank
    • megatron.core.parallel_state.get_data_parallel_world_size
    • megatron.core.parallel_state.get_embedding_group
    • megatron.core.parallel_state.get_global_memory_buffer
    • megatron.core.parallel_state.get_model_parallel_group
    • megatron.core.parallel_state.get_pipeline_model_parallel_first_rank
    • megatron.core.parallel_state.get_pipeline_model_parallel_group
    • megatron.core.parallel_state.get_pipeline_model_parallel_last_rank
    • megatron.core.parallel_state.get_pipeline_model_parallel_next_rank
    • megatron.core.parallel_state.get_pipeline_model_parallel_prev_rank
    • megatron.core.parallel_state.get_pipeline_model_parallel_rank
    • megatron.core.parallel_state.get_pipeline_model_parallel_world_size
    • megatron.core.parallel_state.get_position_embedding_group
    • megatron.core.parallel_state.get_tensor_model_parallel_group
    • megatron.core.parallel_state.get_tensor_model_parallel_rank
    • megatron.core.parallel_state.get_tensor_model_parallel_src_rank
    • megatron.core.parallel_state.get_tensor_model_parallel_world_size
    • megatron.core.parallel_state.get_virtual_pipeline_model_parallel_rank
    • megatron.core.parallel_state.get_virtual_pipeline_model_parallel_world_size
    • megatron.core.parallel_state.initialize_model_parallel
    • megatron.core.parallel_state.is_pipeline_first_stage
    • megatron.core.parallel_state.is_pipeline_last_stage
    • megatron.core.parallel_state.is_pipeline_stage_after_split
    • megatron.core.parallel_state.is_pipeline_stage_at_split
    • megatron.core.parallel_state.is_pipeline_stage_before_split
    • megatron.core.parallel_state.is_rank_in_embedding_group
    • megatron.core.parallel_state.is_rank_in_position_embedding_group
    • megatron.core.parallel_state.model_parallel_is_initialized
    • megatron.core.parallel_state.set_pipeline_model_parallel_rank
    • megatron.core.parallel_state.set_pipeline_model_parallel_split_rank
    • megatron.core.parallel_state.set_pipeline_model_parallel_world_size
    • megatron.core.parallel_state.set_tensor_model_parallel_rank
    • megatron.core.parallel_state.set_tensor_model_parallel_world_size
    • megatron.core.parallel_state.set_virtual_pipeline_model_parallel_rank
  • megatron.core.utils
    • megatron.core.utils.GlobalMemoryBuffer
    • megatron.core.utils.MakeViewlessTensor
    • megatron.core.utils.assert_viewless_tensor
    • megatron.core.utils.divide
    • megatron.core.utils.ensure_divisibility
    • megatron.core.utils.make_viewless_tensor
    • megatron.core.utils.safely_set_viewless_tensor_data
  • megatron.core.tensor_parallel.cross_entropy
    • megatron.core.tensor_parallel.cross_entropy.vocab_parallel_cross_entropy
    • megatron.core.tensor_parallel.cross_entropy.vocab_parallel_max_indices
  • megatron.core.tensor_parallel.data
    • megatron.core.tensor_parallel.data.broadcast_data
  • megatron.core.tensor_parallel.layers
    • megatron.core.tensor_parallel.layers.ColumnParallelLinear
    • megatron.core.tensor_parallel.layers.LinearWithGradAccumulationAndAsyncCommunication
    • megatron.core.tensor_parallel.layers.RowParallelLinear
    • megatron.core.tensor_parallel.layers.VocabParallelEmbedding
    • megatron.core.tensor_parallel.layers.copy_tensor_model_parallel_attributes
    • megatron.core.tensor_parallel.layers.linear_with_grad_accumulation_and_async_allreduce
    • megatron.core.tensor_parallel.layers.param_is_not_tensor_parallel_duplicate
    • megatron.core.tensor_parallel.layers.set_defaults_if_not_set_tensor_model_parallel_attributes
    • megatron.core.tensor_parallel.layers.set_tensor_model_parallel_attributes
  • megatron.core.tensor_parallel.mappings
    • megatron.core.tensor_parallel.mappings.copy_to_tensor_model_parallel_region
    • megatron.core.tensor_parallel.mappings.gather_from_sequence_parallel_region
    • megatron.core.tensor_parallel.mappings.gather_from_tensor_model_parallel_region
    • megatron.core.tensor_parallel.mappings.reduce_from_tensor_model_parallel_region
    • megatron.core.tensor_parallel.mappings.reduce_scatter_to_sequence_parallel_region
    • megatron.core.tensor_parallel.mappings.scatter_to_sequence_parallel_region
    • megatron.core.tensor_parallel.mappings.scatter_to_tensor_model_parallel_region
  • megatron.core.tensor_parallel.random
    • megatron.core.tensor_parallel.random.CheckpointFunction
    • megatron.core.tensor_parallel.random.CudaRNGStatesTracker
    • megatron.core.tensor_parallel.random.checkpoint
    • megatron.core.tensor_parallel.random.get_cuda_rng_tracker
    • megatron.core.tensor_parallel.random.model_parallel_cuda_manual_seed
  • megatron.core.tensor_parallel.utils
    • megatron.core.tensor_parallel.utils.VocabUtility
    • megatron.core.tensor_parallel.utils.gather_split_1d_tensor
    • megatron.core.tensor_parallel.utils.split_tensor_along_last_dim
    • megatron.core.tensor_parallel.utils.split_tensor_into_1d_equal_chunks
  • megatron.data.autoaugment
    • megatron.data.autoaugment.ImageNetPolicy
    • megatron.data.autoaugment.SubPolicy
  • megatron.data.blendable_dataset
    • megatron.data.blendable_dataset.BlendableDataset
  • megatron.data.gpt_dataset
    • megatron.data.gpt_dataset.GPTDataset
    • megatron.data.gpt_dataset.build_train_valid_test_datasets
    • megatron.data.gpt_dataset.get_indexed_dataset_
  • megatron.data.image_folder
    • megatron.data.image_folder.DatasetFolder
    • megatron.data.image_folder.ImageFolder
    • megatron.data.image_folder.accimage_loader
    • megatron.data.image_folder.default_loader
    • megatron.data.image_folder.has_file_allowed_extension
    • megatron.data.image_folder.is_image_file
    • megatron.data.image_folder.make_dataset
    • megatron.data.image_folder.pil_loader
  • megatron.data.realm_dataset_utils
    • megatron.data.realm_dataset_utils.BlockSampleData
    • megatron.data.realm_dataset_utils.BlockSamplesMapping
    • megatron.data.realm_dataset_utils.get_block_samples_mapping
    • megatron.data.realm_dataset_utils.get_ict_batch
    • megatron.data.realm_dataset_utils.get_one_epoch_dataloader
    • megatron.data.realm_dataset_utils.join_str_list
  • megatron.data.bert_dataset
    • megatron.data.bert_dataset.BertDataset
    • megatron.data.bert_dataset.build_training_sample
    • megatron.data.bert_dataset.pad_and_convert_to_numpy
  • megatron.data.data_samplers
    • megatron.data.data_samplers.MegatronPretrainingRandomSampler
    • megatron.data.data_samplers.MegatronPretrainingSampler
    • megatron.data.data_samplers.RandomSeedDataset
    • megatron.data.data_samplers.build_pretraining_data_loader
  • megatron.data.indexed_dataset
    • megatron.data.indexed_dataset.IndexedCachedDataset
    • megatron.data.indexed_dataset.IndexedDataset
    • megatron.data.indexed_dataset.IndexedDatasetBuilder
    • megatron.data.indexed_dataset.MMapIndexedDataset
    • megatron.data.indexed_dataset.MMapIndexedDatasetBuilder
    • megatron.data.indexed_dataset.code
    • megatron.data.indexed_dataset.create_doc_idx
    • megatron.data.indexed_dataset.data_file_path
    • megatron.data.indexed_dataset.dataset_exists
    • megatron.data.indexed_dataset.get_available_dataset_impl
    • megatron.data.indexed_dataset.index_file_path
    • megatron.data.indexed_dataset.infer_dataset_impl
    • megatron.data.indexed_dataset.make_builder
    • megatron.data.indexed_dataset.make_dataset
    • megatron.data.indexed_dataset.read_longs
    • megatron.data.indexed_dataset.write_longs
  • megatron.data.orqa_wiki_dataset
    • megatron.data.orqa_wiki_dataset.OpenRetrievalEvidenceDataset
    • megatron.data.orqa_wiki_dataset.build_sample
    • megatron.data.orqa_wiki_dataset.build_tokens_types_paddings_from_ids
    • megatron.data.orqa_wiki_dataset.build_tokens_types_paddings_from_text
    • megatron.data.orqa_wiki_dataset.get_open_retrieval_batch
    • megatron.data.orqa_wiki_dataset.get_open_retrieval_wiki_dataset
  • megatron.data.realm_index
    • megatron.data.realm_index.FaissMIPSIndex
    • megatron.data.realm_index.OpenRetreivalDataStore
    • megatron.data.realm_index.detach
  • megatron.data.biencoder_dataset_utils
    • megatron.data.biencoder_dataset_utils.BlockSampleData
    • megatron.data.biencoder_dataset_utils.BlockSamplesMapping
    • megatron.data.biencoder_dataset_utils.get_block_samples_mapping
    • megatron.data.biencoder_dataset_utils.get_ict_batch
    • megatron.data.biencoder_dataset_utils.get_one_epoch_dataloader
    • megatron.data.biencoder_dataset_utils.join_str_list
    • megatron.data.biencoder_dataset_utils.make_attention_mask
  • megatron.data.dataset_utils
    • megatron.data.dataset_utils.MaskedLmInstance
    • megatron.data.dataset_utils.build_train_valid_test_datasets
    • megatron.data.dataset_utils.compile_helper
    • megatron.data.dataset_utils.create_masked_lm_predictions
    • megatron.data.dataset_utils.create_tokens_and_tokentypes
    • megatron.data.dataset_utils.get_a_and_b_segments
    • megatron.data.dataset_utils.get_datasets_weights_and_num_samples
    • megatron.data.dataset_utils.get_indexed_dataset_
    • megatron.data.dataset_utils.get_samples_mapping
    • megatron.data.dataset_utils.get_train_valid_test_split_
    • megatron.data.dataset_utils.is_start_piece
    • megatron.data.dataset_utils.pad_and_convert_to_numpy
    • megatron.data.dataset_utils.truncate_segments
  • megatron.data.ict_dataset
    • megatron.data.ict_dataset.ICTDataset
    • megatron.data.ict_dataset.get_ict_dataset
    • megatron.data.ict_dataset.make_attention_mask
  • megatron.data.t5_dataset
    • megatron.data.t5_dataset.T5Dataset
    • megatron.data.t5_dataset.build_training_sample
    • megatron.data.t5_dataset.make_attention_mask
    • megatron.data.t5_dataset.make_attention_mask_3d
    • megatron.data.t5_dataset.make_history_mask
    • megatron.data.t5_dataset.make_history_mask_3d
    • megatron.data.t5_dataset.pad_and_convert_to_numpy
  • megatron.model.bert_model
    • megatron.model.bert_model.BertLMHead
    • megatron.model.bert_model.BertModel
    • megatron.model.bert_model.bert_extended_attention_mask
    • megatron.model.bert_model.bert_position_ids
    • megatron.model.bert_model.post_language_model_processing
  • megatron.model.biencoder_model
    • megatron.model.biencoder_model.BiEncoderModel
    • megatron.model.biencoder_model.PretrainedBertModel
    • megatron.model.biencoder_model.biencoder_model_provider
    • megatron.model.biencoder_model.get_model_provider
  • megatron.model.classification
    • megatron.model.classification.Classification
  • megatron.model.distributed
    • megatron.model.distributed.DistributedDataParallel
    • megatron.model.distributed.DistributedDataParallelBase
    • megatron.model.distributed.MemoryBuffer
  • megatron.model.enums
    • megatron.model.enums.AttnMaskType
    • megatron.model.enums.AttnType
    • megatron.model.enums.LayerType
    • megatron.model.enums.ModelType
    • megatron.model.enums.PositionEmbeddingType
  • megatron.model.falcon_model
    • megatron.model.falcon_model.FalconModel
  • megatron.model.fused_bias_gelu
    • megatron.model.fused_bias_gelu.GeLUFunction
  • megatron.model.fused_layer_norm
    • megatron.model.fused_layer_norm.FusedLayerNormAffineFunction
    • megatron.model.fused_layer_norm.MixedFusedLayerNorm
    • megatron.model.fused_layer_norm.RMSNorm
  • megatron.model.fused_softmax
    • megatron.model.fused_softmax.FusedScaleMaskSoftmax
    • megatron.model.fused_softmax.ScaledMaskedSoftmax
    • megatron.model.fused_softmax.ScaledSoftmax
    • megatron.model.fused_softmax.ScaledUpperTriangMaskedSoftmax
  • megatron.model.glu_activations
    • megatron.model.glu_activations.GEGLU
    • megatron.model.glu_activations.LiGLU
    • megatron.model.glu_activations.ReGLU
    • megatron.model.glu_activations.SwiGLU
  • megatron.model.gpt_model
    • megatron.model.gpt_model.GPTModel
    • megatron.model.gpt_model.post_language_model_processing
  • megatron.model.language_model
    • megatron.model.language_model.Embedding
    • megatron.model.language_model.Pooler
    • megatron.model.language_model.TransformerLanguageModel
    • megatron.model.language_model.get_language_model
    • megatron.model.language_model.parallel_lm_logits
  • megatron.model.llama_model
    • megatron.model.llama_model.LlamaModel
  • megatron.model.module
    • megatron.model.module.Float16Module
    • megatron.model.module.MegatronModule
    • megatron.model.module.conversion_helper
    • megatron.model.module.float16_to_fp32
    • megatron.model.module.fp32_to_float16
    • megatron.model.module.param_is_not_shared
  • megatron.model.multiple_choice
    • megatron.model.multiple_choice.MultipleChoice
  • megatron.model.positional_embeddings
    • megatron.model.positional_embeddings.apply_rotary_emb
    • megatron.model.positional_embeddings.precompute_freqs_cis
    • megatron.model.positional_embeddings.reshape_for_broadcast
  • megatron.model.t5_model
    • megatron.model.t5_model.T5LMHead
    • megatron.model.t5_model.T5Model
    • megatron.model.t5_model.t5_extended_attention_mask
    • megatron.model.t5_model.t5_position_ids
  • megatron.model.transformer
    • megatron.model.transformer.CoreAttention
    • megatron.model.transformer.DropPath
    • megatron.model.transformer.NoopTransformerLayer
    • megatron.model.transformer.ParallelAttention
    • megatron.model.transformer.ParallelMLP
    • megatron.model.transformer.ParallelTransformer
    • megatron.model.transformer.ParallelTransformerLayer
    • megatron.model.transformer.bias_dropout_add
    • megatron.model.transformer.dropout_add
    • megatron.model.transformer.get_bias_dropout_add
    • megatron.model.transformer.get_dropout_add
  • megatron.model.utils
    • megatron.model.utils.attention_mask_func
    • megatron.model.utils.get_linear_layer
    • megatron.model.utils.init_method_normal
    • megatron.model.utils.scaled_init_method_normal
  • megatron.optimizer.clip_grads
    • megatron.optimizer.clip_grads.clip_grad_norm_fp32
    • megatron.optimizer.clip_grads.count_zeros_fp32
  • megatron.optimizer.distrib_optimizer
    • megatron.optimizer.distrib_optimizer.DistributedOptimizer
    • megatron.optimizer.distrib_optimizer.Range
  • megatron.optimizer.grad_scaler
    • megatron.optimizer.grad_scaler.ConstantGradScaler
    • megatron.optimizer.grad_scaler.DynamicGradScaler
    • megatron.optimizer.grad_scaler.MegatronGradScaler
  • megatron.optimizer.optimizer
    • megatron.optimizer.optimizer.FP32Optimizer
    • megatron.optimizer.optimizer.Float16OptimizerWithFloat16Params
    • megatron.optimizer.optimizer.MegatronOptimizer
    • megatron.optimizer.optimizer.MixedPrecisionOptimizer
  • megatron.text_generation.api
    • megatron.text_generation.api.beam_search
    • megatron.text_generation.api.beam_search_and_post_process
    • megatron.text_generation.api.generate
    • megatron.text_generation.api.generate_and_post_process
  • megatron.text_generation.beam_utils
    • megatron.text_generation.beam_utils.BeamHypotheses
  • megatron.text_generation.communication
    • megatron.text_generation.communication.broadcast_float_list
    • megatron.text_generation.communication.broadcast_from_last_pipeline_stage
    • megatron.text_generation.communication.broadcast_from_last_to_first_pipeline_stage
    • megatron.text_generation.communication.broadcast_int_list
    • megatron.text_generation.communication.broadcast_list
    • megatron.text_generation.communication.broadcast_tensor
    • megatron.text_generation.communication.copy_from_last_to_first_pipeline_stage
    • megatron.text_generation.communication.recv_from_prev_pipeline_rank_
    • megatron.text_generation.communication.send_to_next_pipeline_rank
  • megatron.text_generation.forward_step
    • megatron.text_generation.forward_step.ForwardStep
    • megatron.text_generation.forward_step.InferenceParams
  • megatron.text_generation.generation
    • megatron.text_generation.generation.beam_search_and_return_on_first_stage
    • megatron.text_generation.generation.generate_tokens_probs_and_return_on_first_stage
    • megatron.text_generation.generation.score_and_return_on_first_stage
  • megatron.text_generation.sampling
    • megatron.text_generation.sampling.modify_logits_for_top_k_filtering
    • megatron.text_generation.sampling.modify_logits_for_top_p_filtering
    • megatron.text_generation.sampling.sample
  • megatron.text_generation.tokenization
    • megatron.text_generation.tokenization.detokenize_generations
    • megatron.text_generation.tokenization.tokenize_prompts
  • megatron.tokenizer.bert_tokenization
    • megatron.tokenizer.bert_tokenization.BasicTokenizer
    • megatron.tokenizer.bert_tokenization.FullTokenizer
    • megatron.tokenizer.bert_tokenization.WordpieceTokenizer
    • megatron.tokenizer.bert_tokenization.convert_by_vocab
    • megatron.tokenizer.bert_tokenization.convert_ids_to_tokens
    • megatron.tokenizer.bert_tokenization.convert_to_unicode
    • megatron.tokenizer.bert_tokenization.convert_tokens_to_ids
    • megatron.tokenizer.bert_tokenization.load_vocab
    • megatron.tokenizer.bert_tokenization.printable_text
    • megatron.tokenizer.bert_tokenization.validate_case_matches_checkpoint
    • megatron.tokenizer.bert_tokenization.whitespace_tokenize
  • megatron.tokenizer.gpt2_tokenization
    • megatron.tokenizer.gpt2_tokenization.GPT2Tokenizer
    • megatron.tokenizer.gpt2_tokenization.bytes_to_unicode
    • megatron.tokenizer.gpt2_tokenization.get_pairs
  • megatron.tokenizer.tokenizer
    • megatron.tokenizer.tokenizer.AbstractTokenizer
    • megatron.tokenizer.tokenizer.build_tokenizer
  • API
  • megatron.data.realm_index
  • megatron.dat...

megatron.data.realm_index.detach#

megatron.data.realm_index.detach(tensor)#

previous

megatron.data.realm_index.OpenRetreivalDataStore

next

megatron.data.biencoder_dataset_utils

On this page
  • detach()
Show Source

© Copyright 2023, Alejandro Hernández Cano, Matteo Pagliardini, Kyle Matoba, Amirkeivan Mohtashami, Olivia Simin Fan, Axel Marmet, Deniz Bayazit, Igor Krawczuk, Zeming Chen, Francesco Salvi, Antoine Bosselut, Martin Jaggi.

Created using Sphinx 7.1.0.

Built with the PyData Sphinx Theme 0.15.2.