optimum-intel-internal-testing/tiny-random-aya-base
Original1.1Mparameters
Fixture16.9Mparameters
Layer stacks1compared
Findings2to review
⚠ To review
- optimum-intel-internal-testing/tiny-random-aya-base is a test checkpoint (untrained): build from a trained checkpoint of this model type
- the fixture keeps 1583% of the original's 1.1M 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.layers
Original · 2
Fixture · 2
| Kind | Original | Fixture | |
|---|---|---|---|
| DecoderLayer | 2 | 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.embed_tokens | 1.0M | 98.4% | 16.8M | 99.5% |
| model.layers | 16.5K | 1.6% | 82.0K | 0.5% |
| model.norm | 4 | 0.0% | 64 | 0.0% |
Preserved properties
| Config | Property | Original | Fixture | |
|---|---|---|---|---|
| model | attention style | MHA (4 heads, 4 KV) | MHA (4 heads, 4 KV) | ✓ kept |
| model | RoPE type | default | default | ✓ kept |
| model | model_type | cohere2 | cohere2 | ✓ kept |
| model | vocab_size | 262144 | 262144 | ✓ kept |
| model | tie_word_embeddings | True | True | ✓ kept |
| model | hidden_act | silu | silu | ✓ kept |
| model | max_position_embeddings | 500000 | 500000 | ✓ kept |
Module classes
Instances of each class in the built model (prefix Cohere2 omitted).
| Class | Original | Fixture |
|---|---|---|
| Linear | 15 | 15 |
| LayerNorm | 3 | 3 |
| Attention | 2 | 2 |
| DecoderLayer | 2 | 2 |
| MLP | 2 | 2 |
| SiLUActivation | 2 | 2 |
| ForCausalLM | 1 | 1 |
| Model | 1 | 1 |
| RotaryEmbedding | 1 | 1 |
| Embedding | 1 | 1 |
| ModuleList | 1 | 1 |
Config changes
3 fields changed, 40 unchanged.
| Field | Original | Fixture |
|---|---|---|
| head_dim | 128 | 16 |
| hidden_size | 4 | 64 |
| intermediate_size | 5 | 128 |