Downloads · 30 days
22
8% of all-time downloads
embeddinggemma-300m-distilled-width10pct-128dim-best
Pieces/embeddinggemma-300m-distilled-width10pct-128dim-best
embeddinggemma-300m-distilled-width10pct-128dim-best is a feature extraction model from Pieces. Use it when you need embeddings to search or compare text. It is set up for sentence-transformers.
This is a distilled/compressed version of google/embeddinggemma-300m.
All-time downloads
277
Public
Parameters
19.8M
117 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors79.3 MB · 67%
At a glance
- Task
- Feature Extraction
- Library
- sentence-transformers
- Model type
- gemma3_text
- Access
- Public
- Created
- Dec 23, 2025
- Updated
- Dec 23, 2025
- SHA
- 34de2116
Base models
Model card
From the Hugging Face model README
Distilled Backbone: embeddinggemma-300m-distilled-10pct-128dim
This is a distilled/compressed version of google/embeddinggemma-300m.
Compression Details
- Base model: google/embeddinggemma-300m
- Width reduction factor: 0.1
- Target hidden size: 72
- Final embedding dimension: 128
- Had projection layer: True
- Projection incorporated: True
Usage
To use this as a pretrained backbone in validation:
python -m playground.validate_from_checkpoint \
--pretrained_backbone_model "Pieces/embeddinggemma-300m-distilled-width10pct-128dim-best" \
--backbone_embedding_dim 128 \
--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 128 directly, incorporating any projection layers from the distillation process.
- Task
- Feature Extraction
- Library
- sentence-transformers
- Type
- gemma3_text
- Created
- Dec 23, 2025
- Updated
- Dec 23, 2025