huggingface / nanoVLM Conditional Complexity

Intro

Conditional complexity (also called cyclomatic complexity) is a term used to measure the complexity of software. The term refers to the number of possible paths through a program function. A higher value ofter means higher maintenance and testing costs (infosecinstitute.com).
Conditional complexity is calculated by counting all conditions in the program that can affect the execution path (e.g. if statement, loops, switches, and/or operators, try and catch blocks...).
Conditional complexity is measured at the unit level (methods, functions...).
Units are classified in four categories based on the measured McCabe index: 1-5 (simple units), 6-10 (medium complex units), 11-25 (complex units), 26+ (very complex units).

Learn more...

Conditional Complexity Overall

There are 104 units with 1,972 lines of code in units (21.4% of code).

0 very complex units (0 lines of code)
5 complex units (634 lines of code)
6 medium complex units (261 lines of code)
12 simple units (296 lines of code)
81 very simple units (781 lines of code)

Legend:

51+

26-50

11-25

6-10

1-5

Alternative Visuals

3D view of all units

Conditional Complexity per Extension

51+

26-50

11-25

6-10

1-5

Conditional Complexity per Logical Component

primary logical decomposition

51+

26-50

11-25

6-10

1-5

Most Complex Units

Top 50 most complex units

Unit	# lines	McCabe index	# params
def cli_evaluate_single() in evaluation.py	142	49	2
def train() in train.py	236	33	2
def measure_vram() in eval/measure_vram.py	117	33	3
def cli_evaluate() in evaluation.py	80	32	2
def generate_until() in eval/lmms_eval_wrapper.py	59	26	2
def from_pretrained() in models/language_model.py	79	24	2
def generate() in models/vision_language_model.py	61	21	9
def forward() in models/language_model.py	47	15	6
def main() in train.py	35	12	0
def _prepare_visual_input() in eval/lmms_eval_wrapper.py	19	12	2
def _int_or_none_list_arg_type() in evaluation.py	20	11	6
def from_pretrained() in models/vision_transformer.py	64	10	2
def forward() in models/language_model.py	14	9	5
def get_dataloaders() in train.py	53	8	2
def __iter__() in data/advanced_datasets.py	26	8	1
def forward() in models/vision_language_model.py	14	8	5
def check_multiple_choice_with_regex() in models/utils.py	16	7	2
def get_lr() in train.py	11	6	3
def synchronized_dataloader_step() in data/data_utils.py	18	6	2
def prepare_batch() in data/collators.py	15	6	3
def main() in generate.py	25	6	0
def generate() in models/language_model.py	28	6	3
def _init_weights() in models/vision_transformer.py	12	6	2
def _pad_batch() in data/collators.py	4	5	3
def forward() in models/language_model.py	15	5	2
def _init_weights() in models/language_model.py	9	5	2
def forward() in models/vision_transformer.py	23	5	2
def check_argument_types() in evaluation.py	7	5	1
def _process_images() in data/datasets.py	11	4	2
def _prepare_inputs_and_loss_mask() in data/datasets.py	20	4	2
def _pad_batch() in data/collators.py	4	4	3
def _discard_samples_that_are_too_long() in data/collators.py	10	4	3
def get_tokenizer() in data/processors.py	11	4	3
def main() in eval/measure_vram.py	16	4	0
def __init__() in models/vision_transformer.py	14	4	2
def _handle_non_serializable() in evaluation.py	7	4	1
def _get_messages() in data/datasets.py	8	3	3
def _pack_one_group() in data/advanced_datasets.py	10	3	4
def flatten() in eval/lmms_eval_wrapper.py	6	3	2
def apply_rotary_pos_embd() in models/language_model.py	6	3	5
def __init__() in models/language_model.py	19	3	2
def __init__() in models/language_model.py	15	3	2
def top_k_top_p_filtering() in models/utils.py	13	3	4
def forward() in models/vision_transformer.py	9	3	2
def forward() in models/vision_transformer.py	10	3	2
def _init_weights() in models/modality_projector.py	5	3	2
def is_dist() in train.py	2	2	0
def is_master() in train.py	2	2	0
def get_world_size() in train.py	2	2	0
def get_rank() in train.py	2	2	0