stAvI Vionano — BF16
The full-precision BF16 safetensors release of stAvI Vionano. This is the base for anyone who wants to quantize, fine-tune further, or run the model in their own setup.
For the ready-to-run MLX version optimized for iPhone 15 Pro and newer, see gleraTech/stAvI-Vionano.
Model Details
- Base model: Qwen/Qwen3-1.7B
- Finetuning: Unsloth, 3000 examples, custom stAvI dataset
- Format: BF16 safetensors
- Languages: German, English
What is stAvI Vionano?
stAvI Vionano is the built-in offline assistant shipped with the stAvI iOS app by gleraTech solutions Austria GmbH. It runs entirely on-device and takes over automatically whenever the cloud model is unreachable.
Response Format
<response>
<thinking>
Internal reasoning here.
</thinking>
<answer>
Answer here.
</answer>
</response>
Credits
- Qwen Team for Qwen3-1.7B
- Unsloth for fast finetuning
- gleraTech solutions Austria GmbH for finetuning
License
Apache 2.0
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support