Model reference · open weights
all-MiniLM-L6-onnx is an open-weight embedding model from onnx-models.
For self-hosting, compare this build's requirements below with the GPU you plan to rent.
Summary of the onnx-models/all-MiniLM-L6-v2-onnx model card, 2026-10-01
What it is
| Released by | onnx-models |
|---|---|
| Released | 2024-07-27 |
From the model card
This is the ONNX-ported version of the sentence-transformers/all-MiniLM-L6-v2 for generating text embeddings.
Using this model becomes easy when you have light-embed installed:
pip install -U light-embed
Then you can use the model by specifying the original model name like this:
from light_embed import TextEmbedding
sentences = [
"This is an example sentence",
"Each sentence is converted"
]
model = TextEmbedding('sentence-transformers/all-MiniLM-L6-v2')
embeddings = model.encode(sentences)
print(embeddings)
or by specifying the onnx model name like this:
from light_embed import TextEmbedding
sentences = [
"This is an example sentence",
"Each sentence is converted"
]
model = TextEmbedding('onnx-models/all-MiniLM-L6-v2-onnx')
embeddings = model.encode(sentences)
print(embeddings)
Binh Nguyen / binhcode25@gmail.com
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.