← MIC coverage of Transformers model types

IDEA-Research/grounding-dino-tiny

huggingface-mic/grounding-dino-tiny-mic@fb3535345454 ← IDEA-Research/grounding-dino-tiny@a2bb814dd30d · GroundingDinoForObjectDetection · random weights · built before the shrink rule (no recorded recipe)

CI: no failure on main in 30 days · MIC failures dashboard

Original172.3Mparameters

Fixture7.7Mparameters

Layer stacks7compared

Findings0to review

✓ Same architecture, smaller

Every module class, layer kind and checked property of the original is in the fixture.

Layer stacks

One square per layer, colored by kind: the layer's module classes and type attributes. Hover a square for its index and kind.

model.backbone.conv_encoder.model.swin.encoder.layers

Original · 4

Fixture · 4

Kind	Original	Fixture
SwinPatchMerging	3	3	✓ kept
no SwinPatchMerging	1	1	✓ kept

model.input_proj_vision

Original · 4

Fixture · 4

Kind	Original	Fixture
Conv2d	4	4	✓ kept

model.text_backbone.encoder.layer

Original · 12

Fixture · 2

Kind	Original	Fixture
BertLayer	12	2	✓ kept

model.encoder.layers

Original · 6

Fixture · 2

Kind	Original	Fixture
FusionLayer	6	2	✓ kept

model.decoder.layers

Original · 6

Fixture · 2

Kind	Original	Fixture
DecoderLayer	6	2	✓ kept

model.decoder.bbox_embed

Original · 6

Fixture · 2

Kind	Original	Fixture
Linear	6	2	✓ kept

bbox_embed

Original · 6

Fixture · 2

Kind	Original	Fixture
Linear	6	2	✓ kept

Where the parameters are

Share of each model's parameters per component. Vocabulary and patch sizes are kept, so embeddings usually take a larger share of the fixture.

Original

Fixture

Component	Original	Share	Fixture	Share
model.text_backbone.encoder.layer	85.1M	49.4%	66.9K	0.9%
model.backbone.conv_encoder.model.swin.encoder.layers	27.5M	16.0%	4.9M	63.4%
model.text_backbone	23.8M	13.8%	2.0M	25.7%
model.encoder.layers	21.9M	12.7%	176.4K	2.3%
model.decoder.layers	10.9M	6.3%	142.3K	1.8%
model.input_proj_vision	2.1M	1.2%	353.0K	4.6%
model.query_position_embeddings	230.4K	0.1%	57.6K	0.7%
8 others	736.2K	0.4%	44.5K	0.6%

Preserved properties

Config	Property	Original	Fixture
model	model_type	grounding-dino	grounding-dino	✓ kept
model	tie_word_embeddings	True	True	✓ kept
backbone_config	model_type	swin	swin	✓ kept
backbone_config	hidden_act	gelu	gelu	✓ kept
backbone_config	image_size	224	224	✓ kept
backbone_config	patch_size	4	4	✓ kept
backbone_config	num_channels	3	3	✓ kept
text_config	model_type	bert	bert	✓ kept
text_config	vocab_size	30522	30522	✓ kept
text_config	tie_word_embeddings	True	True	✓ kept
text_config	hidden_act	gelu	gelu	✓ kept
text_config	max_position_embeddings	512	512	✓ kept

Module classes

Instances of each class in the built model (prefix GroundingDino omitted).

Class	Original	Fixture
Linear	382	122
LayerNorm	119	43
Dropout	68	18
ModuleList	26	18
GELUActivation	24	6
MultiheadAttention	18	6
ReLU	18	6
MLPPredictionHead	14	6
BertAttention	12	2
BertIntermediate	12	2
BertLayer	12	2
BertOutput	12	2
BertSelfAttention	12	2
BertSelfOutput	12	2
MultiscaleDeformableAttention	12	4
MultiScaleDeformableAttention	12	4
SwinAttention	12	4
SwinLayer	12	4
SwinMLP	12	4
SwinRelativePositionBias	12	4
SwinDropPath	11	3
ContrastiveEmbedding	7	3
BiMultiHeadAttention	6	2
DecoderLayer	6	2
DeformableLayer	6	2
DropPath	6	2
EncoderLayer	6	2
FusionLayer	6	2
TextEnhancerLayer	6	2
Conv2d	5	5
Embedding	4	4
GroupNorm	4	4
Sequential	4	4
SwinStage	4	4
SwinPatchMerging	3	3
BertEmbeddings	1	1
BertEncoder	1	1
BertModel	1	1
ConvEncoder	1	1
ConvModel	1	1
Decoder	1	1
Encoder	1	1
ForObjectDetection	1	1
Model	1	1
SinePositionEmbedding	1	1
Identity	1	1
ModuleDict	1	1
SwinBackbone	1	1
SwinEmbeddings	1	1
SwinEncoder	1	1
SwinModel	1	1
SwinPatchEmbeddings	1	1

Config changes

16 fields changed, 91 unchanged.

Field	Original	Fixture
backbone_config.depths	[2, 2, 6, 2]	[1, 1, 1, 1]
backbone_config.embed_dim	96	64
backbone_config.hidden_size	768	64
backbone_config.num_heads	[3, 6, 12, 24]	[2, 4, 8, 16]
backbone_config.num_layers	4	2
d_model	256	64
decoder_attention_heads	8	4
decoder_ffn_dim	2048	128
decoder_layers	6	2
encoder_attention_heads	8	4
encoder_ffn_dim	2048	128
encoder_layers	6	2
text_config.hidden_size	768	64
text_config.intermediate_size	3072	128
text_config.num_attention_heads	12	4
text_config.num_hidden_layers	12	2