Instructions to use KitsuMate/all-MiniLM-L6-v2-onnx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- sentence-transformers
How to use KitsuMate/all-MiniLM-L6-v2-onnx with sentence-transformers:
from sentence_transformers import SentenceTransformer model = SentenceTransformer("KitsuMate/all-MiniLM-L6-v2-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] - Notebooks
- Google Colab
- Kaggle
all-MiniLM-L6-v2 ONNX
KitsuMate packaging of sentence-transformers/all-MiniLM-L6-v2 for Unity ONNX inference.
The upstream checkpoint is pinned at 1110a243fdf4706b3f48f1d95db1a4f5529b4d41. The original authors and Sentence Transformers project retain authorship. This repository provides ONNX files using the standard flat onnx/ layout.
ONNX artifacts
| File | Size | SHA-256 | Engines |
|---|---|---|---|
onnx/model.onnx |
90,405,214 bytes | 6fd5d72fe4589f189f8ebc006442dbb529bb7ce38f8082112682524616046452 |
ONNX Runtime, com.unity.ai.inference 2.6.1 |
onnx/model_q4f16.onnx |
109,149 bytes | 6297f8bb2f10987bad6f36d06022bb4b4ff5289247654843d599389630fd53dd |
ONNX Runtime |
onnx/model_q4f16.onnx_data |
29,826,048 bytes | e37a0ad962e125f02213afef98d52a606331a1c95a56c6e01d320fefb83892a2 |
External data for Q4F16 |
tokenizer.json |
533,808 bytes | 07805d116826679de90b4edeb2222269c4b8753bc0981be4399f732b2708e904 |
Shared |
vocab.txt |
231,508 bytes | 07eced375cec144d27c900241f3e339478dec958f92fddbc551f295c992038a3 |
Shared |
The unsuffixed file is the default FP32 artifact. Artifact types are derived from standard filename suffixes; no custom manifest is required.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support