tryaii-minilm-int8
v1.0.0
Published
The embedding model of the tryaii SDK: all-MiniLM-L6-v2 as an int8 ONNX file (run with onnxruntime-node).
Readme
tryaii-minilm-int8
The local embedding model of the tryaii SDK:
all-MiniLM-L6-v2
(Apache-2.0) exported to ONNX with int8 weights, run on onnxruntime.
Install it next to onnxruntime-node to enable local classification in the monitor: npm install onnxruntime-node tryaii-minilm-int8 (both are optional peer dependencies of tryaii).
It contains one 23.0 MB file, model.onnx
(sha256 8199be6f699a395f99f89df973f9dc5285fbcfcdb2ae1a4e1201dab014f3d2a6),
which tryaii verifies before it uses it. Prompts are embedded on your machine;
nothing is downloaded at run time.
On a machine that cannot install it, place the file anywhere and set
TRYAII_EMBEDDING_MODEL_PATH to it.
Built by scripts/export-onnx-embedding.py in the tryaii repository.
