Skip to content

sura:0.8b

3 TagsUpdated 0.8B params8192 contextEnglishApache-2.0by Ollaya

Qwen3.5-0.8B: 0.560 on typed decisions, zero-shot; 60 ms for five questions on an RTX 5090.

0.8b
ollaya run sura:0.8b --preset triage "I was charged twice for my subscription this month and want a refund."

Details

  • graph38b6a8bf9074 · 8 MBonnx · pplx · 0.8B · fp32
  • weightsf5bd00594d50 · 1.7 GBhuggingface.co/ollaya-dev/sura-0.8b/resolve/9e991fa…/model.safetensors
  • weightsd51e8cdec401 · 522 KBhuggingface.co/ollaya-dev/sura-0.8b/resolve/9e991fa…/readout.safetensors
  • tokenizer6f32ce20dc35 · 20 MBhuggingface.co/ollaya-dev/sura-0.8b/resolve/9e991fa…/tokenizer.json
  • decisioneef33f2fe2ea · 6 KB{"engine": "onnx", "family": "pplx", "encoder": "", "layout": "pplx-joint-v1", …}
  • calibration4480c0e1f156 · 181 B{"temperature": [0.93, 0.93, 0.93]}
  • licensee883397b3998 · 11 KBSura by Ollaya (https://huggingface.co/ollaya-dev)

Every layer is checked against its sha256 when it is pulled. Weights and tokenizers download from the model author's Hugging Face repository at a pinned commit; Ollaya never re-hosts them.

sura readme and all models