Downloads · 30 days
0
weave-eng/qwen3-embedding-0.6b-onnx-router
qwen3-embedding-0.6b-onnx-router is a machine learning model from weave-eng. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
INT8 ONNX export of Qwen/Qwen3-Embedding-0.6B (Apache-2.0) used by the Weave router's cluster scorer. Produced by scripts/exportqwen3onnx.py in the workweave/router repo.
Downloads · 30 days
0
Access
Public
Updated Jun 10, 2026
Repo size
3.4 GB
Likes
0
Public
Click a slice to open those files.
.data2.4 GB · 69%
From the Hugging Face model README
INT8 ONNX export of Qwen/Qwen3-Embedding-0.6B
(Apache-2.0) used by the Weave router's cluster scorer. Produced by
scripts/export_qwen3_onnx.py in the workweave/router repo.
| File | Purpose |
|---|---|
model.onnx | INT8 dynamic quantization, deployed artifact |
model_fp32.onnx + .data | fp32 export, provenance only (not deployed) |
tokenizer.json, tokenizer_config.json | HF tokenizer |
fixture.json | Go parity-test fixture (mirrors internal/router/cluster/testdata/fixture_qwen3.json) |
sentence_embedding [batch, 1024]. No L2 norm in the graph
(the router's hugot pipeline applies it).down_proj (3072x1024)
and o_proj (2048x1024) MatMuls kept fp32 (outlier-sensitive activations).The router Dockerfile pins HF_QWEN_REVISION to a commit SHA of this repo.
Revisions are immutable; pushing a new export here never changes deployed
images until the pin is bumped deliberately.