• File size measurements show the distribution of size of files.
• Files are classified in four categories based on their size (lines of code): 1-100 (very small files), 101-200 (small files), 201-500 (medium size files), 501-1000 (long files), 1001+(very long files).
• It is a good practice to keep files small. Long files may become "bloaters", code that have increased to such gargantuan proportions that they are hard to work with.

• There are 280 files with 72,165 lines of code.
• 9 very long files (11,322 lines of code)
• 40 long files (25,686 lines of code)
• 60 medium size files (21,834 lines of codeclsfd_ftr_w_mp_ins)
• 57 small files (8,197 lines of code)
• 114 very small files (5,126 lines of code)

There are 80 files with lines longer than 120 characters. In total, there are 305 long lines.

File	# lines	# units	# long lines
hf2mcore_deepseek_v3_moe.py in toolkits/model_checkpoints_convertor/deepseek	578	12	34
hf2mcore_qwen2_moe.py in toolkits/model_checkpoints_convertor/qwen	555	11	20
hf2mcore_deepseek_v2_moe.py in toolkits/model_checkpoints_convertor/deepseek	454	8	16
hf2mcore_qwen2_dense_and_moe_gqa.py in toolkits/model_checkpoints_convertor/qwen	821	10	15
m2h_synchronizer.py in toolkits/distributed_checkpoints_convertor/impl/general	499	17	13
hf2megatron_qwen1.5.py in toolkits/model_checkpoints_convertor/qwen	810	15	12
hf2megatron.py in toolkits/model_checkpoints_convertor/llama	808	15	10
hf2mcore_qwen2_vl.py in toolkits/model_checkpoints_convertor/qwen	616	10	9
hf2mcore_qwen2.5_vl.py in toolkits/model_checkpoints_convertor/qwen	607	10	8
dataset_helpers.py in megatron_patch/data	381	9	8
convert.py in toolkits/distributed_checkpoints_convertor/impl	80	2	7
hf2mcore_mixtral.py in toolkits/model_checkpoints_convertor/mistral	672	10	5
hf2mcore_qwen1.5_moe.py in toolkits/model_checkpoints_convertor/qwen	479	12	5
hf2megablocks_qwen1.5.py in toolkits/model_checkpoints_convertor/qwen	546	19	5
transformer_config.py in megatron_patch/model/mixtral_bak	142	1	5
transformer.py in megatron_patch/model/baichuan2	1292	36	5
__init__.py in toolkits/model_checkpoints_convertor/utils	146	5	4
checkpoint_reshaping_and_interoperability.py in toolkits/model_checkpoints_convertor/falcon	612	12	4
transformer.py in megatron_patch/model/llava	1292	35	4
transformer.py in megatron_patch/model/mistral	1292	35	4
transformer.py in megatron_patch/model/qwen_vl	1292	35	4
transformer.py in megatron_patch/model/llama2	1296	35	4
transformer_legacy.py in megatron_patch/model/llama3	1252	36	4
transformer.py in megatron_patch/model/qwen	1243	35	4
build_llava_frame_dataset.py in toolkits/multimodal_data_preprocessing	123	5	3
preprocess_data_megatron.py in toolkits/pretrain_data_preprocessing	360	13	3
synchronizer.py in toolkits/distributed_checkpoints_convertor/impl/general	119	9	3
checkpoint_reshaping_and_interoperability.py in toolkits/model_checkpoints_convertor/falcon40b	583	12	3
hf2te.py in toolkits/model_checkpoints_convertor/baichuan	378	8	3
checkpoint_reshaping_and_interoperability.py in toolkits/model_checkpoints_convertor/yi	468	13	3
__init__.py in megatron_patch/data	88	7	3
language_model.py in megatron_patch/model/llava	507	16	3
transformer.py in megatron_patch/model/qwen1_5_megablocks	1184	35	3
language_model.py in megatron_patch/model/baichuan	515	20	3
transformer.py in megatron_patch/model/baichuan	1179	32	3
checkpoint_reshaping_and_interoperability.py in toolkits/model_checkpoints_convertor/baichuan	649	14	2
checkpoint_reshaping_and_interoperability.py in toolkits/model_checkpoints_convertor/galactica	454	13	2
hf2mcore_qwen1.5_dense_mha.py in toolkits/model_checkpoints_convertor/qwen	280	10	2
hf2megatron_qwen1.0.py in toolkits/model_checkpoints_convertor/qwen	725	15	2
gpt_model.py in megatron_patch/model/llava	89	6	2
clip_encoder.py in megatron_patch/model/llava	75	10	2
gpt_model.py in megatron_patch/model/qwen1_5_megablocks	88	6	2
gpt_model.py in megatron_patch/model/mistral	88	6	2
modeling_attn_mask_utils.py in megatron_patch/model/mistral	121	8	2
gpt_model.py in megatron_patch/model/baichuan	106	7	2
transformer.py in megatron_patch/model/bloom	811	27	2
gpt_model.py in megatron_patch/model/baichuan2	97	6	2
gpt_model.py in megatron_patch/model/qwen_vl	89	6	2
transformer.py in megatron_patch/model/falcon	845	31	2
gpt_model.py in megatron_patch/model/llama2	88	6	2