Downloads · 30 days
5
11% of all-time downloads
mole-minilm-l6-fp16
latentdivergence/mole-minilm-l6-fp16
mole-minilm-l6-fp16 is a feature extraction model from latentdivergence. Use it when you need embeddings to search or compare text. It is set up for transformers.js. The card lists the license as apache-2.0.
A fp16 ONNX build of onnx-community/all-MiniLM-L6-v2-ONNX, mirrored as the pinned download source for the Mole AI browser extension.
All-time downloads
44
Public
Repo size
45.2 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx_data45.1 MB · 99%
At a glance
- Task
- Feature Extraction
- Library
- transformers.js
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Jul 19, 2026
- Updated
- Jul 20, 2026
- SHA
- 660f77df
Base models
Model card
From the Hugging Face model README
burrow-minilm-l6-fp16
A fp16 ONNX build of onnx-community/all-MiniLM-L6-v2-ONNX, mirrored
as the pinned download source for the Mole AI browser extension.
The weights are byte-identical to the upstream export by onnx-community; nothing was re-quantised or fine-tuned here. This repo exists so the extension depends on a copy that cannot be renamed or deleted out from under its installed users.
Only the files the browser runtime loads are included -- the fp16 graph plus
tokenizer and config. For every other precision, use the upstream repo.
Use
import { pipeline } from "@huggingface/transformers";
const pipe = await pipeline("text-generation", "latentdivergence/burrow-minilm-l6-fp16", {
dtype: "fp16",
device: "webgpu",
});
Licensed as per the base model.
- Task
- Feature Extraction
- Library
- transformers.js
- Type
- bert
- License
- apache-2.0
- Created
- Jul 19, 2026
- Updated
- Jul 20, 2026