optimum-intel-internal-testing/tiny-random-muse-glimmer
Original13.5Mparameters
Fixture13.3Mparameters
Layer stacks2compared
Findings2to review
⚠ To review
- optimum-intel-internal-testing/tiny-random-muse-glimmer is a test checkpoint (untrained): build from a trained checkpoint of this model type
- the fixture keeps 98% of the original's 13.5M parameters
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.vision_tower.layers
Original · 4
Fixture · 2
| Kind | Original | Fixture | |
|---|---|---|---|
| VisionEncoderLayer | 4 | 2 | ✓ kept |
model.language_model.layers
Original · 4
Fixture · 2
| Kind | Original | Fixture | |
|---|---|---|---|
| TextDecoderLayer | 4 | 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.language_model | 12.9M | 95.6% | 12.9M | 97.4% |
| model.language_model.layers | 263.2K | 1.9% | 82.4K | 0.6% |
| model.vision_tower | 141.1K | 1.0% | 141.1K | 1.1% |
| model.vision_tower.layers | 133.9K | 1.0% | 66.9K | 0.5% |
| model.vision_adapter | 49.2K | 0.4% | 49.2K | 0.4% |
| model.vision_projection | 8.2K | 0.1% | 8.2K | 0.1% |
Preserved properties
| Config | Property | Original | Fixture | |
|---|---|---|---|---|
| model | model_type | muse_glimmer | muse_glimmer | ✓ kept |
| model | tie_word_embeddings | True | True | ✓ kept |
| text_config | attention style | GQA (4 heads, 2 KV) | GQA (4 heads, 2 KV) | ✓ kept |
| text_config | RoPE type | default | default | ✓ kept |
| text_config | model_type | muse_glimmer_text | muse_glimmer_text | ✓ kept |
| text_config | vocab_size | 202048 | 202048 | ✓ kept |
| text_config | tie_word_embeddings | True | True | ✓ kept |
| text_config | max_position_embeddings | 131072 | 131072 | ✓ kept |
| vision_config | RoPE type | axial | axial | ✓ kept |
| vision_config | model_type | muse_glimmer_vision | muse_glimmer_vision | ✓ kept |
| vision_config | hidden_act | gelu | gelu | ✓ kept |
| vision_config | max_position_embeddings | 1024 | 1024 | ✓ kept |
| vision_config | patch_size | 14 | 14 | ✓ kept |
Module classes
Instances of each class in the built model (prefix MuseGlimmer omitted).
| Class | Original | Fixture |
|---|---|---|
| Linear | 61 | 33 |
| TextCenteredRMSNorm | 16 | 8 |
| LayerNorm | 10 | 6 |
| RMSNorm | 7 | 5 |
| GELUActivation | 5 | 3 |
| TextAttention | 4 | 2 |
| TextDecoderLayer | 4 | 2 |
| TextMLP | 4 | 2 |
| VisionAttention | 4 | 2 |
| VisionEncoderLayer | 4 | 2 |
| VisionMLP | 4 | 2 |
| SiLUActivation | 4 | 2 |
| ModuleList | 2 | 2 |
| Embedding | 1 | 1 |
| ForConditionalGeneration | 1 | 1 |
| Model | 1 | 1 |
| TextModel | 1 | 1 |
| TextNormedEmbedding | 1 | 1 |
| TextRotaryEmbedding | 1 | 1 |
| VisionAdapter | 1 | 1 |
| VisionModel | 1 | 1 |
| VisionPatchEmbedder | 1 | 1 |
| VisionRotaryEmbedding | 1 | 1 |
Config changes
6 fields changed, 67 unchanged.
| Field | Original | Fixture |
|---|---|---|
| text_config.intermediate_size | 256 | 128 |
| text_config.layer_rope_theta | [500000.0, 500000.0, 500000.0, 0] | [500000.0, 0] |
| text_config.layer_types | ["sliding_attention", "sliding_attention", "sliding_attention", "full_attenti… | ["sliding_attention", "full_attention"] |
| text_config.num_hidden_layers | 4 | 2 |
| vision_config.layer_types | ["window_attention", "window_attention", "window_attention", "full_attention"] | ["window_attention", "full_attention"] |
| vision_config.num_hidden_layers | 4 | 2 |