← MIC coverage of Transformers model types

thhaus/nemotron3-8b

huggingface-mic/nemotron3-8b-mic@6b1234b7b072 ← thhaus/nemotron3-8b@0a670790a587 · NemotronForCausalLM · random weights

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

Original8.5Bparameters
Fixture32.8Mparameters
Layer stacks1compared
Findings0to review

✓ Same architecture, smaller

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

Model tester (advisory)

The model's own small test config in its ModelTester (16 literal values, 0 set by the model's own tester, the rest generic base-tester defaults). Testers are usually representative but not always, so these notes are for review, not rules.

The fixture covers every per-layer kind the tester sets, and shrinks every size it does.

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.layers

Original · 32
Fixture · 2
KindOriginalFixture
DecoderLayer322✓ 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
model.layers6.4B75.4%66.0K0.2%
model.embed_tokens1.0B12.3%16.4M49.9%
lm_head1.0B12.3%16.4M49.9%
model.norm8.2K0.0%1280.0%

Preserved properties

ConfigPropertyOriginalFixture
modelattention styleMHA (32 heads, 32 KV)MHA (4 heads, 4 KV)✓ kept
modelRoPE typedefaultdefault✓ kept
modelmodel_typenemotronnemotron✓ kept
modelvocab_size256000256000✓ kept
modeltie_word_embeddingsFalseFalse✓ kept
modelhidden_actrelu2relu2✓ kept
modelmax_position_embeddings40964096✓ kept

Module classes

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

ClassOriginalFixture
Linear19313
LayerNorm1P655
Attention322
DecoderLayer322
MLP322
ReLUSquaredActivation322
Embedding11
ModuleList11
ForCausalLM11
Model11
RotaryEmbedding11

Config changes

6 fields changed, 23 unchanged.

FieldOriginalFixture
head_dim12816
hidden_size409664
intermediate_size16384128
num_attention_heads324
num_hidden_layers322
num_key_value_heads324