# Distilled Backbone: embeddinggemma-300m-distilled-768dim

This is a distilled/compressed version of google/embeddinggemma-300m.

## Compression Details
- Base model: google/embeddinggemma-300m
- Width reduction factor: None
- Target hidden size: None
- Final embedding dimension: 768
- Had projection layer: False
- Projection incorporated: False

## Usage

To use this as a pretrained backbone in validation:

```bash
python -m playground.validate_from_checkpoint \
    --pretrained_backbone_model "Pieces/embeddinggemma-300m-distilled-depth33pct-40-768dim-step72000" \
    --backbone_embedding_dim 768 \
    --backbone_pooling_mode "mean" \
    --num_samples 100 \
    --dataset_split "val" \
    --num_general_tags_high 100 \
    --num_general_tags_low 100
```

**Important**: The path must point to the `sentence_transformer` subdirectory (not the parent directory).

The exported model has been configured to output embeddings of dimension 768 directly, incorporating any projection layers from the distillation process.