baai-llm-embedder-onnx

LightEmbed/baai-llm-embedder-onnx

This is the ONNX version of the Sentence Transformers model BAAI/llm-embedder for sentence embedding, optimized for speed and lightweight performance. By utilizing onnxruntime and tokenizers instead of heavier libraries like sentence-transformers and transformers, this version ensures a smaller library size and faster execution. Below are the details of the model:

• Base model: BAAI/llm-embedder
• Embedding dimension: 768
• Max sequence length: 512
• File size on disk: 0.41 GB
• Pooling incorporated: Yes

This ONNX model consists all components in the original sentence transformer model: Transformer, Pooling, Normalize

<!--- Describe your model here -->

Usage (LightEmbed)

Using this model becomes easy when you have LightEmbed installed:

pip install -U light-embed

Then you can use the model using the original model name like this:

from light_embed import TextEmbedding
sentences = [
	"This is an example sentence",
	"Each sentence is converted"
]

model = TextEmbedding('BAAI/llm-embedder')
embeddings = model.encode(sentences)
print(embeddings)

Then you can use the model using onnx model name like this:

from light_embed import TextEmbedding
sentences = [
	"This is an example sentence",
	"Each sentence is converted"
]

model = TextEmbedding('LightEmbed/baai-llm-embedder-onnx')
embeddings = model.encode(sentences)
print(embeddings)

Citing & Authors

Binh Nguyen / [email protected]