embeddinggemma-qat-q8_0-unquantized

Model Page: EmbeddingGemma

Resources and Technical Documentation:

• Responsible Generative AI Toolkit
• EmbeddingGemma on Vertex Model Garden

Terms of Use: Terms

Authors: Google DeepMind

Model Information

Description

EmbeddingGemma is a 300M parameter, state-of-the-art for its size, open embedding model from Google, built from Gemma 3 (with T5Gemma initialization) and the same research and technology used to create Gemini models. EmbeddingGemma produces vector representations of text, making it well-suited for search and retrieval tasks, including classification, clustering, and semantic similarity search. This model was trained with data in 100+ spoken languages.

The small size and on-device focus makes it possible to deploy in environments with limited resources such as mobile phones, laptops, or desktops, democratizing access to state of the art AI models and helping foster innovation for everyone.

Inputs and outputs

• Input:

  • Text string, such as a question, a prompt, or a document to be embedded
  • Maximum input context length of 2048 tokens

• Output:

  • Numerical vector representations of input text data
  • Output embedding dimension size of 768, with smaller options available (512, 256, or 128) via Matryoshka Representation Learning (MRL). MRL allows users to truncate the output embedding of size 768 to their desired size and then re-normalize for efficient and accurate representation.

Usage

These model weights are designed to be used with Sentence Transformers, using the Gemma 3 implementation from Hugging Face Transformers as the backbone.

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("google/embeddinggemma-300m")

# Run inference with queries and documents
query = "Which planet is known as the Red Planet?"
documents = [
    "Venus is often called Earth's twin because of its similar size and proximity.",
    "Mars, known for its reddish appearance, is often referred to as the Red Planet.",
    "Jupiter, the largest planet in our solar system, has a prominent red spot.",
    "Saturn, famous for its rings, is sometimes mistaken for the Red Planet."
]
query_embeddings = model.encode_query(query)
document_embeddings = model.encode_document(documents)
print(query_embeddings.shape, document_embeddings.shape)
# (768,) (4, 768)

# Compute similarities to determine a ranking
similarities = model.similarity(query_embeddings, document_embeddings)
print(similarities)
# tensor([[0.3011, 0.6359, 0.4930, 0.4889]])

NOTE: EmbeddingGemma activations do not support float16. Please use float32 or bfloat16 as appropriate for your hardware.

Model Data

Training Dataset

This model was trained on a dataset of text data that includes a wide variety of sources totaling approximately 320 billion tokens. Here are the key components:

• Web Documents: A diverse collection of web text ensures the model is exposed to a broad range of linguistic styles, topics, and vocabulary. The training dataset includes content in over 100 languages.
• Code and Technical Documents: Exposing the model to code and technical documentation helps it learn the structure and patterns of programming languages and specialized scientific content, which improves its understanding of code and technical questions.
• Synthetic and Task-Specific Data: Synthetically training data helps to teach the model specific skills. This includes curated data for tasks like information retrieval, classification, and sentiment analysis, which helps to fine-tune its performance for common embedding applications.

The combination of these diverse data sources is crucial for training a powerful multilingual embedding model that can handle a wide variety of different tasks and data formats.

Data Preprocessing

Here are the key data cleaning and filtering methods applied to the training data:

• CSAM Filtering: Rigorous CSAM (Child Sexual Abuse Material) filtering was applied at multiple stages in the data preparation process to ensure the exclusion of harmful and illegal content.
• Sensitive Data Filtering: As part of making Gemma pre-trained models safe and reliable, automated techniques were used to filter out certain personal information and other sensitive data from training sets.
• Additional methods: Filtering based on content quality and safety in line with our policies.

Model Development

Hardware

EmbeddingGemma was trained using the latest generation of Tensor Processing Unit (TPU) hardware (TPUv5e), for more details refer to the Gemma 3 model card.

Software

Training was done using JAX and ML Pathways. For more details refer to the Gemma 3 model card.

Evaluation

Benchmark Results

The model was evaluated against a large collection of different datasets and metrics to cover different aspects of text understanding.

Full Precision Checkpoint

QAT Checkpoints

Note: QAT models are evaluated after quantization

* Mixed Precision refers to per-