Downloads · 30 days
9
1% of all-time downloads
Qwen3-0.6B-sharepoint-tools-ONNX
esperz/Qwen3-0.6B-sharepoint-tools-ONNX
Qwen3-0.6B-sharepoint-tools-ONNX is a text generation model from esperz. Use it when you need the model to write or continue text. It is set up for transformers.js. The card lists the license as apache-2.0.
A LoRA fine-tune of Qwen/Qwen3-0.6B that routes SharePoint page-designer tool calls (generatemarkdown, createpage, updateimage, updatetitle, updatetext, or a clarifying question) from a 15-token system prompt — no inl…
All-time downloads
889
Public
Repo size
4.4 GB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.onnx2.4 GB · 99%
At a glance
- Task
- Text Generation
- Library
- transformers.js
- License
- apache-2.0
- Model type
- qwen3
- Access
- Public
- Created
- Jul 3, 2026
- Updated
- Jul 4, 2026
- SHA
- acb36cf9
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3-0.6B — SharePoint tool-calling fine-tune (ONNX, q4)
A LoRA fine-tune of Qwen/Qwen3-0.6B that routes SharePoint page-designer tool calls
(generate_markdown, create_page, update_image, update_title, update_text, or a clarifying
question) from a 15-token system prompt — no inline tool definitions.
Exported to ONNX and quantized to 4-bit (MatMulNBits) for in-browser inference with
Transformers.js. Load with dtype: "q4".
Why
The base model needs a ~1,120-token system prompt + tool schema to route correctly. Baking the protocol into the weights lets the prompt shrink ~67×.
Results (200-example routing eval, shrunk prompt)
| Model | Top-1 accuracy |
|---|---|
| Base Qwen3-0.6B | 10.0% |
| This fine-tune | 100.0% |
System prompt
You are a SharePoint page designer. Build and refine pages by calling tools.
Built with the pipeline in training/fine-tuning/py (see the client-ai-fabric repo, docs/14).
- Task
- Text Generation
- Library
- transformers.js
- Type
- qwen3
- License
- apache-2.0
- Created
- Jul 3, 2026
- Updated
- Jul 4, 2026