Qwen/Qwen2.5-VL-3B-Instruct
Original3.8Bparameters
Fixture11.3Mparameters
Layer stacks2compared
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.
model.visual.blocks
Original · 32
Fixture · 32
| Kind | Original | Fixture | |
|---|---|---|---|
| VisionBlock | 32 | 32 | ✓ kept |
model.language_model.layers
Original · 36
Fixture · 2
| Kind | Original | Fixture | |
|---|---|---|---|
| DecoderLayer | 36 | 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.layers | 2.8B | 73.9% | 74.2K | 0.7% |
| model.visual.blocks | 630.5M | 16.8% | 1.3M | 11.8% |
| model.language_model | 311.2M | 8.3% | 9.7M | 86.1% |
| model.visual | 38.2M | 1.0% | 157.6K | 1.4% |
Preserved properties
| Config | Property | Original | Fixture | |
|---|---|---|---|---|
| model | model_type | qwen2_5_vl | qwen2_5_vl | ✓ kept |
| model | tie_word_embeddings | True | True | ✓ kept |
| text_config | attention style | GQA (16 heads, 2 KV) | GQA (4 heads, 2 KV) | ✓ kept |
| text_config | RoPE type | default | default | ✓ kept |
| text_config | model_type | qwen2_5_vl_text | qwen2_5_vl_text | ✓ kept |
| text_config | vocab_size | 151936 | 151936 | ✓ kept |
| text_config | hidden_act | silu | silu | ✓ kept |
| text_config | max_position_embeddings | 128000 | 128000 | ✓ kept |
| vision_config | RoPE type | axial | axial | ✓ kept |
| vision_config | model_type | qwen2_5_vl_vision | qwen2_5_vl_vision | ✓ kept |
| vision_config | hidden_act | silu | silu | ✓ kept |
| vision_config | patch_size | 14 | 14 | ✓ kept |
Module classes
Instances of each class in the built model (prefix Qwen2_5_VL omitted).
| Class | Original | Fixture |
|---|---|---|
| Linear | 415 | 177 |
| RMSNorm | 138 | 70 |
| SiLUActivation | 68 | 34 |
| Qwen2MLP | 36 | 2 |
| Attention | 36 | 2 |
| DecoderLayer | 36 | 2 |
| MLP | 32 | 32 |
| VisionAttention | 32 | 32 |
| VisionBlock | 32 | 32 |
| ModuleList | 2 | 2 |
| Conv3d | 1 | 1 |
| Embedding | 1 | 1 |
| GELU | 1 | 1 |
| ForConditionalGeneration | 1 | 1 |
| Model | 1 | 1 |
| PatchMerger | 1 | 1 |
| RotaryEmbedding | 1 | 1 |
| TextModel | 1 | 1 |
| VisionRotaryEmbedding | 1 | 1 |
| Qwen2_5_VisionPatchEmbed | 1 | 1 |
| Qwen2_5_VisionTransformerPretrainedModel | 1 | 1 |
| Sequential | 1 | 1 |
Config changes
10 fields changed, 60 unchanged.
| Field | Original | Fixture |
|---|---|---|
| text_config.hidden_size | 2048 | 64 |
| text_config.intermediate_size | 11008 | 128 |
| text_config.layer_types | 36 entries: 36× full_attention | ["full_attention", "full_attention"] |
| text_config.num_attention_heads | 16 | 4 |
| text_config.num_hidden_layers | 36 | 2 |
| text_config.rope_parameters | {"type": "mrope", "mrope_section": [16, 24, 24], "rope_theta": 1000000.0, "ro… | {"mrope_section": [2, 3, 3], "rope_theta": 1000000.0, "rope_type": "default",… |
| vision_config.hidden_size | 1280 | 64 |
| vision_config.intermediate_size | 3420 | 128 |
| vision_config.num_heads | 16 | 4 |
| vision_config.out_hidden_size | 2048 | 64 |