huggingface / nanoVLM Unit Size

Intro

Unit size measurements show the distribution of size of units of code (methods, functions...).
Units are classified in four categories based on their size (lines of code): 1-20 (small units), 20-50 (medium size units), 51-100 (long units), 101+ (very long units).
You should aim at keeping units small (< 20 lines). Long units may become "bloaters", code that have increased to such gargantuan proportions that they are hard to work with.

Learn more...

Unit Size Overall

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

4 very long units (682 lines of code)
6 long units (396 lines of code)
6 medium size units (184 lines of code)
27 small units (409 lines of code)
61 very small units (301 lines of code)

Legend:

101+

51-100

21-50

11-20

1-10

Unit Size per Extension

101+

51-100

21-50

11-20

1-10

Unit Size per Logical Component

primary logical decomposition

101+

51-100

21-50

11-20

1-10

Alternative Visuals

3D view of all units

Longest Units

Top 50 longest units

Unit	# lines	McCabe index	# params
def train() in train.py	236	33	2
def parse_eval_args() in evaluation.py	187	2	0
def cli_evaluate_single() in evaluation.py	142	49	2
def measure_vram() in eval/measure_vram.py	117	33	3
def cli_evaluate() in evaluation.py	80	32	2
def from_pretrained() in models/language_model.py	79	24	2
def from_pretrained() in models/vision_transformer.py	64	10	2
def generate() in models/vision_language_model.py	61	21	9
def generate_until() in eval/lmms_eval_wrapper.py	59	26	2
def get_dataloaders() in train.py	53	8	2
def forward() in models/language_model.py	47	15	6
def main() in train.py	35	12	0
def generate() in models/language_model.py	28	6	3
def __iter__() in data/advanced_datasets.py	26	8	1
def main() in generate.py	25	6	0
def forward() in models/vision_transformer.py	23	5	2
def _prepare_inputs_and_loss_mask() in data/datasets.py	20	4	2
def parse_args() in generate.py	20	1	0
def _int_or_none_list_arg_type() in evaluation.py	20	11	6
def __getitem__() in data/datasets.py	19	1	2
def _prepare_visual_input() in eval/lmms_eval_wrapper.py	19	12	2
def __init__() in models/language_model.py	19	3	2
def __init__() in models/vision_transformer.py	19	2	2
def synchronized_dataloader_step() in data/data_utils.py	18	6	2
def main() in eval/measure_vram.py	16	4	0
def check_multiple_choice_with_regex() in models/utils.py	16	7	2
def __getitem__() in data/datasets.py	15	2	2
def prepare_batch() in data/collators.py	15	6	3
def forward() in models/language_model.py	15	5	2
def __init__() in models/language_model.py	15	3	2
def push_to_hub() in models/vision_language_model.py	15	1	3
def forward() in models/language_model.py	14	9	5
def forward() in models/vision_language_model.py	14	8	5
def __init__() in models/vision_transformer.py	14	4	2
def top_k_top_p_filtering() in models/utils.py	13	3	4
def __init__() in models/vision_language_model.py	13	2	3
def pixel_shuffle() in models/modality_projector.py	13	2	2
def _init_weights() in models/vision_transformer.py	12	6	2
def get_run_name() in train.py	11	2	2
def get_lr() in train.py	11	6	3
def _process_images() in data/datasets.py	11	4	2
def get_tokenizer() in data/processors.py	11	4	3
def benchmark_vlm() in eval/benchmark_suite.py	11	1	0
def _discard_samples_that_are_too_long() in data/collators.py	10	4	3
def __init__() in data/advanced_datasets.py	10	1	0
def _pack_one_group() in data/advanced_datasets.py	10	3	4
def __init__() in models/language_model.py	10	2	2
def forward() in models/language_model.py	10	1	6
def forward() in models/vision_transformer.py	10	3	2
def _init_weights() in models/language_model.py	9	5	2