← MIC coverage of Transformers model types

ibm-granite/granite-3.0-1b-a400m-instruct

huggingface-mic/granite-3.0-1b-a400m-instruct-mic@62c5d85c9097 ← ibm-granite/granite-3.0-1b-a400m-instruct@ffec3c35bdfd · GraniteMoeForCausalLM · random weights

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

Original1.3Bparameters
Fixture3.4Mparameters
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 (19 literal values, 3 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 · 24
Fixture · 2
KindOriginalFixture
DecoderLayer242✓ 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.layers1.3B96.2%222.0K6.6%
model.embed_tokens50.3M3.8%3.1M93.4%
model.norm1.0K0.0%640.0%

Preserved properties

ConfigPropertyOriginalFixture
modelattention styleGQA (16 heads, 8 KV)GQA (4 heads, 2 KV)✓ kept
modelMoE routingtop-8 of 32 expertstop-2 of 4 experts✓ kept
modelRoPE typedefaultdefault✓ kept
modelmodel_typegranitemoegranitemoe✓ kept
modelvocab_size4915549155✓ kept
modeltie_word_embeddingsTrueTrue✓ kept
modelhidden_actsilusilu✓ kept
modelmax_position_embeddings40964096✓ kept

Module classes

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

ClassOriginalFixture
Linear979
RMSNorm495
Attention242
DecoderLayer242
Experts242
MoE242
TopKRouter242
SiLUActivation242
Embedding11
ForCausalLM11
Model11
RotaryEmbedding11
ModuleList11

Config changes

7 fields changed, 28 unchanged.

FieldOriginalFixture
hidden_size102464
intermediate_size512128
num_attention_heads164
num_experts_per_tok82
num_hidden_layers242
num_key_value_heads82
num_local_experts324