LICENSE
README.md
pyproject.toml
src/megatron/bridge/__init__.py
src/megatron/bridge/package_info.py
src/megatron/bridge/data/__init__.py
src/megatron/bridge/data/loaders.py
src/megatron/bridge/data/samplers.py
src/megatron/bridge/data/utils.py
src/megatron/bridge/data/builders/__init__.py
src/megatron/bridge/data/builders/finetuning_dataset.py
src/megatron/bridge/data/builders/hf_dataset.py
src/megatron/bridge/data/datasets/__init__.py
src/megatron/bridge/data/datasets/packed_sequence.py
src/megatron/bridge/data/datasets/packing_utils.py
src/megatron/bridge/data/datasets/sft.py
src/megatron/bridge/data/datasets/utils.py
src/megatron/bridge/data/hf_processors/__init__.py
src/megatron/bridge/data/hf_processors/squad.py
src/megatron/bridge/models/__init__.py
src/megatron/bridge/models/config.py
src/megatron/bridge/models/gpt_full_te_layer_autocast_spec.py
src/megatron/bridge/models/gpt_provider.py
src/megatron/bridge/models/model_provider.py
src/megatron/bridge/models/t5_provider.py
src/megatron/bridge/models/conversion/__init__.py
src/megatron/bridge/models/conversion/auto_bridge.py
src/megatron/bridge/models/conversion/mapping_registry.py
src/megatron/bridge/models/conversion/model_bridge.py
src/megatron/bridge/models/conversion/param_mapping.py
src/megatron/bridge/models/conversion/utils.py
src/megatron/bridge/models/decorators/__init__.py
src/megatron/bridge/models/decorators/dispatch.py
src/megatron/bridge/models/decorators/torchrun.py
src/megatron/bridge/models/hf_pretrained/__init__.py
src/megatron/bridge/models/hf_pretrained/base.py
src/megatron/bridge/models/hf_pretrained/causal_lm.py
src/megatron/bridge/models/hf_pretrained/state.py
src/megatron/bridge/models/hf_pretrained/vlm.py
src/megatron/bridge/models/llama/__init__.py
src/megatron/bridge/models/llama/llama4_utils.py
src/megatron/bridge/models/llama/llama_bridge.py
src/megatron/bridge/models/llama/llama_provider.py
src/megatron/bridge/models/mamba/__init__.py
src/megatron/bridge/models/mamba/mamba_provider.py
src/megatron/bridge/models/mamba/nemotron_h_provider.py
src/megatron/bridge/models/qwen/__init__.py
src/megatron/bridge/models/qwen/qwen2_bridge.py
src/megatron/bridge/models/qwen/qwen3_bridge.py
src/megatron/bridge/models/qwen/qwen3_moe_bridge.py
src/megatron/bridge/models/qwen/qwen_provider.py
src/megatron/bridge/peft/__init__.py
src/megatron/bridge/peft/adapter_wrapper.py
src/megatron/bridge/peft/base.py
src/megatron/bridge/peft/canonical_lora.py
src/megatron/bridge/peft/dora.py
src/megatron/bridge/peft/dora_layers.py
src/megatron/bridge/peft/lora.py
src/megatron/bridge/peft/lora_layers.py
src/megatron/bridge/peft/module_matcher.py
src/megatron/bridge/peft/utils.py
src/megatron/bridge/peft/walk_utils.py
src/megatron/bridge/recipes/run_plugins.py
src/megatron/bridge/recipes/llama/llama2_7b.py
src/megatron/bridge/recipes/llama/llama31_405b.py
src/megatron/bridge/recipes/llama/llama31_70b.py
src/megatron/bridge/recipes/llama/llama31_8b.py
src/megatron/bridge/recipes/llama/llama32_1b.py
src/megatron/bridge/recipes/llama/llama32_3b.py
src/megatron/bridge/recipes/llama/llama3_70b.py
src/megatron/bridge/recipes/llama/llama3_70b_16k.py
src/megatron/bridge/recipes/llama/llama3_70b_64k.py
src/megatron/bridge/recipes/llama/llama3_8b.py
src/megatron/bridge/recipes/llama/llama3_8b_128k.py
src/megatron/bridge/recipes/llama/llama3_8b_16k.py
src/megatron/bridge/recipes/llama/llama3_8b_64k.py
src/megatron/bridge/recipes/llama/llama4_e128.py
src/megatron/bridge/recipes/llama/llama4_e16.py
src/megatron/bridge/recipes/mamba/mamba2_130m.py
src/megatron/bridge/recipes/mamba/mamba2_1_3b.py
src/megatron/bridge/recipes/mamba/mamba2_2_7b.py
src/megatron/bridge/recipes/mamba/mamba2_370m.py
src/megatron/bridge/recipes/mamba/mamba2_780m.py
src/megatron/bridge/recipes/mamba/mamba2_8b.py
src/megatron/bridge/recipes/mamba/mamba2_hybrid_8b.py
src/megatron/bridge/recipes/mamba/nemotron_nano_12b_v2.py
src/megatron/bridge/recipes/mamba/nemotron_nano_9b_v2.py
src/megatron/bridge/recipes/mamba/nemotronh_47b.py
src/megatron/bridge/recipes/mamba/nemotronh_4b.py
src/megatron/bridge/recipes/mamba/nemotronh_56b.py
src/megatron/bridge/recipes/mamba/nemotronh_8b.py
src/megatron/bridge/recipes/utils/__init__.py
src/megatron/bridge/recipes/utils/dataset_utils.py
src/megatron/bridge/recipes/utils/nemo_run_utils.py
src/megatron/bridge/recipes/utils/optimizer_utils.py
src/megatron/bridge/recipes/utils/tokenizer_utils.py
src/megatron/bridge/training/__init__.py
src/megatron/bridge/training/checkpointing.py
src/megatron/bridge/training/comm_overlap.py
src/megatron/bridge/training/config.py
src/megatron/bridge/training/eval.py
src/megatron/bridge/training/fault_tolerance.py
src/megatron/bridge/training/finetune.py
src/megatron/bridge/training/gpt_step.py
src/megatron/bridge/training/initialize.py
src/megatron/bridge/training/losses.py
src/megatron/bridge/training/mixed_precision.py
src/megatron/bridge/training/model_load_save.py
src/megatron/bridge/training/nvrx_straggler.py
src/megatron/bridge/training/optim.py
src/megatron/bridge/training/pretrain.py
src/megatron/bridge/training/setup.py
src/megatron/bridge/training/state.py
src/megatron/bridge/training/train.py
src/megatron/bridge/training/mlm_compat/__init__.py
src/megatron/bridge/training/mlm_compat/activations.py
src/megatron/bridge/training/mlm_compat/arguments.py
src/megatron/bridge/training/mlm_compat/model.py
src/megatron/bridge/training/tokenizers/__init__.py
src/megatron/bridge/training/tokenizers/bert_tokenization.py
src/megatron/bridge/training/tokenizers/config.py
src/megatron/bridge/training/tokenizers/gpt2_tokenization.py
src/megatron/bridge/training/tokenizers/multimodal_tokenizer.py
src/megatron/bridge/training/tokenizers/tokenizer.py
src/megatron/bridge/training/utils/__init__.py
src/megatron/bridge/training/utils/checkpoint_utils.py
src/megatron/bridge/training/utils/config_utils.py
src/megatron/bridge/training/utils/flop_utils.py
src/megatron/bridge/training/utils/log_utils.py
src/megatron/bridge/training/utils/moe_token_drop.py
src/megatron/bridge/training/utils/omegaconf_utils.py
src/megatron/bridge/training/utils/sig_utils.py
src/megatron/bridge/training/utils/theoretical_memory_utils.py
src/megatron/bridge/training/utils/train_utils.py
src/megatron/bridge/training/utils/wandb_utils.py
src/megatron/bridge/utils/__init__.py
src/megatron/bridge/utils/common_utils.py
src/megatron/bridge/utils/decorators.py
src/megatron/bridge/utils/fusions.py
src/megatron/bridge/utils/import_utils.py
src/megatron/bridge/utils/instantiate_utils.py
src/megatron/bridge/utils/yaml_utils.py
src/megatron_bridge.egg-info/PKG-INFO
src/megatron_bridge.egg-info/SOURCES.txt
src/megatron_bridge.egg-info/dependency_links.txt
src/megatron_bridge.egg-info/entry_points.txt
src/megatron_bridge.egg-info/requires.txt
src/megatron_bridge.egg-info/top_level.txt