Downloads · 30 days
0
KitsuMate/all-MiniLM-L6-v2-onnx
all-MiniLM-L6-v2-onnx is a machine learning model from KitsuMate. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for onnxruntime. The card lists the license as apache-2.0.
KitsuMate packaging of sentence-transformers/all-MiniLM-L6-v2 for Unity ONNX inference.
Downloads · 30 days
0
Access
Public
Updated Aug 14, 2026
Repo size
220 MB
Likes
0
Public
Click a slice to open those files.
.onnx_data129 MB · 59%
From the Hugging Face model README
KitsuMate packaging of sentence-transformers/all-MiniLM-L6-v2 for Unity ONNX inference.
The upstream checkpoint is pinned at 1110a243fdf4706b3f48f1d95db1a4f5529b4d41. The FP16, Q4, and Q4F16 variants are copied unchanged from onnx-community/all-MiniLM-L6-v2-ONNX revision aff7a1dc4e8a1ea593e6ea21e95c22ef0a25966f. The original authors, Sentence Transformers project, and ONNX Community contributors retain authorship. This repository provides ONNX files using the standard flat onnx/ layout.
| File | Size | SHA-256 | Engines |
|---|---|---|---|
onnx/model.onnx | 90,405,214 bytes | 6fd5d72fe4589f189f8ebc006442dbb529bb7ce38f8082112682524616046452 | ONNX Runtime, com.unity.ai.inference 2.6.1 |
onnx/model_fp16.onnx + .onnx_data | 45,184,187 bytes | See upstream revision | ONNX Runtime |
onnx/model_q4.onnx + .onnx_data | 54,499,359 bytes | See upstream revision | ONNX Runtime |
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.