all-MiniLM-L6-v2 (int8 ONNX), mirror for QuickNotes

An unmodified copy of onnx/model_quantized.onnx from Xenova/all-MiniLM-L6-v2, which is an ONNX conversion of sentence-transformers/all-MiniLM-L6-v2 (Apache-2.0, by the Sentence-Transformers authors). Hosted here so the QuickNotes app does not depend on a third-party repo staying available.

Output: 384-dimensional sentence embeddings (mean pool over the attention mask, then L2 normalize).
Input: BERT uncased WordPiece token ids (vocab.txt included), max 256 tokens.
SHA-256 of onnx/model_quantized.onnx: afdb6f1a0e45b715d0bb9b11772f032c399babd23bfc31fed1c170afc848bdb1

The app checks this hash after downloading and discards any file that does not match.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Arhenniuss/all-MiniLM-L6-v2

Base model

nreimers/MiniLM-L6-H384-uncased

Quantized

sentence-transformers/all-MiniLM-L6-v2

Quantized

(122)

this model