ONNX Quantized versions of google/embeddinggemma-300m-qat-q8_0-unquantized
This repository contains ONNX export and multiple quantized versions of google/embeddinggemma-300m-qat-q8_0-unquantized.
Usage
from sentence_transformers import SentenceTransformer
# Load Int8 model (ARM64 example)
model = SentenceTransformer(
"jrc2139/embeddinggemma-300m-qat-q8_0-unquantized-ONNX",
backend="onnx",
model_kwargs={"file_name": "onnx/model_q4.onnx"},
trust_remote_code=True
)
- Downloads last month
- 7
from sentence_transformers import SentenceTransformer model = SentenceTransformer("jrc2139/embeddinggemma-300m-qat-q8_0-unquantized-ONNX") sentences = [ "The weather is lovely today.", "It's so sunny outside!", "He drove to the stadium." ] embeddings = model.encode(sentences) similarities = model.similarity(embeddings, embeddings) print(similarities.shape) # [3, 3]