ldenoue/sora-qwen3-0.6b-run02-onnx

Source: 🤗text-generationapache-2.0600M activated358 MBother✓ 3 checksumsupdated 56d ago

Sora Qwen3-0.6B Run 02 DPO — WebGPU ONNX

Q4F16 ONNX export of the Sora workplace-coaching fine-tune. This is an experimental prototype, not an HR, legal, clinical, or safety authority.

Load with @huggingface/transformers using task text-generation, device webgpu, and dtype q4f16. Qwen thinking must remain disabled by passing tokenizer_encode_kwargs: { enable_thinking: false } in the text-generation call.

CommentsShare your thoughts and shape the future of sovereign AI.

@ldenoue is unclaimedSign in with the matching Hugging Face account or an organization member account to verify this handle.Claim @ldenoue

Files and sources

✓SourceAvailable on 🤗

✓Checksums3 recorded

3TorrentNot listed

4SwarmNot checked

Source revision: aa103e89f467…
Witnessed: 3 Oct 2026, 13:35 UTC
Weight files: 3
Model size: 358 MB
Downloads · last month: 129
Publisher: Unclaimed

View provenance entry #20557 →

Seed this model

Have the files? Submit a torrent.

Submit a torrent →

>_Package the files with one command

Have the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo ldenoue/sora-qwen3-0.6b-run02-onnx ./model-folder