← MIC coverage of Transformers model types

microsoft/beit-base-patch16-224

huggingface-mic/beit-base-patch16-224-mic@1a760472d6b5 ← microsoft/beit-base-patch16-224@f02e8f77db47 · BeitForImageClassification · random weights

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

Original86.5Mparameters
Fixture187.3Kparameters
Layer stacks1compared
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.

beit.layers

Original · 12
Fixture · 2
KindOriginalFixture
Layer122✓ 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
ComponentOriginalShareFixtureShare
beit.layers85.2M98.4%72.9K38.9%
classifier769.0K0.9%65.0K34.7%
beit.embeddings591.4K0.7%49.3K26.3%
beit.pooler1.5K0.0%1280.1%

Preserved properties

ConfigPropertyOriginalFixture
modelmodel_typebeitbeit✓ kept
modelvocab_size81928192✓ kept
modelhidden_actgelugelu✓ kept
modelimage_size224224✓ kept
modelpatch_size1616✓ kept
modelnum_channels33✓ kept

Module classes

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

ClassOriginalFixture
Linear7313
LayerNorm255
Dropout133
Attention122
Layer122
MLP122
RelativePositionBias122
GELUActivation122
DropPath111
Identity22
Embeddings11
ForImageClassification11
Model11
PatchEmbeddings11
Pooler11
Conv2d11
ModuleList11

Config changes

6 fields changed, 35 unchanged.

FieldOriginalFixture
hidden_size76864
intermediate_size3072128
num_attention_heads124
num_hidden_layers122
out_features["stage12"]["stage2"]
out_indices[12][2]