Path	Lines of Code
megatron_patch/data/dataset_helpers.py	381
megatron_patch/data/json_sft.py	106
megatron_patch/initialize.py	91
megatron_patch/lm_evaluate.py	139
megatron_patch/model/baichuan/language_model.py	515
megatron_patch/model/baichuan/transformer.py	1179
megatron_patch/model/baichuan2/language_model.py	450
megatron_patch/model/baichuan2/transformer.py	1292
megatron_patch/model/deepseek_v2/model.py	181
megatron_patch/model/deepseek_v2/moe/experts.py	676
megatron_patch/model/deepseek_v2/transformer_block.py	377
megatron_patch/model/deepseek_v2/transformer_layer.py	226
megatron_patch/model/falcon/language_model.py	491
megatron_patch/model/falcon/transformer.py	845
megatron_patch/model/falcon40b/language_model.py	491
megatron_patch/model/galactica/language_model.py	501
megatron_patch/model/glm130b/language_model.py	434
megatron_patch/model/llama/language_model.py	501
megatron_patch/model/llama2/language_model.py	454
megatron_patch/model/llama2/transformer.py	1296
megatron_patch/model/llama3/language_model.py	438
megatron_patch/model/llama3/model.py	144
megatron_patch/model/llama3/transformer_legacy.py	1252
megatron_patch/model/llama3_1/model.py	201
megatron_patch/model/llava/language_model.py	507
megatron_patch/model/llava/transformer.py	1292
megatron_patch/model/llava_mcore/llava_model.py	424
megatron_patch/model/llava_mcore/vision/clip_vit_model.py	130
megatron_patch/model/mistral/language_model.py	466
megatron_patch/model/mistral/transformer.py	1292
megatron_patch/model/mixtral/model.py	177
megatron_patch/model/mixtral/moe/experts.py	676
megatron_patch/model/mixtral/transformer_config.py	285
megatron_patch/model/mixtral_bak/model.py	162
megatron_patch/model/mixtral_bak/moe/token_dispatcher.py	172
megatron_patch/model/qwen/language_model.py	440
megatron_patch/model/qwen/transformer.py	1243
megatron_patch/model/qwen1_5/model.py	144
megatron_patch/model/qwen1_5/moe/token_dispatcher.py	282
megatron_patch/model/qwen1_5_megablocks/language_model.py	453
megatron_patch/model/qwen2/model.py	146
megatron_patch/model/qwen2/moe/router.py	206
megatron_patch/model/qwen2/transformer_block.py	323
megatron_patch/model/qwen2/transformer_layer.py	147
megatron_patch/model/qwen2_5_vl/transformer_block.py	434
megatron_patch/model/qwen2_5_vl/visionmodel.py	224
megatron_patch/model/qwen2_vl/visionmodel.py	160
megatron_patch/model/qwen3_moe/moe/moe_utils.py	79
megatron_patch/model/qwen_vl/language_model.py	481
megatron_patch/model/qwen_vl/transformer.py	1292
megatron_patch/model/starcoder/transformer.py	848
megatron_patch/template/helper.py	115
megatron_patch/training.py	612
rlhf/deepspeed-chat/utils.py	204
toolkits/auto_configurator/report_theoretical_memory.py	147
toolkits/model_checkpoints_convertor/deepseek/hf2mcore_deepseek_v3_moe.py	578
toolkits/model_checkpoints_convertor/glm/checkpoint_reshaping_and_interoperability.py	378
toolkits/model_checkpoints_convertor/qwen/hf2mcore_qwen2_moe.py	555