Skip to content

d3:nano

6 TagsUpdated 2B params8192 contextEnglishApache-2.0by vLLM Semantic Router

Qwen3.5-2B: 0.625 on typed decisions, zero-shot.

2b
ollaya run d3:nano --preset triage "I was charged twice for my subscription this month and want a refund."

Details

  • graph6ad16ac210fc · 9 MBonnx · d3 · 2B · fp32
  • weights7269b3260f11 · 4.4 GBhuggingface.co/vllm-sr/d3-nano/resolve/462efc3…/model.safetensors
  • weights662e8a26d801 · 2 MBhuggingface.co/vllm-sr/d3-nano/resolve/462efc3…/readout.safetensors
  • tokenizer06b9509352d2 · 20 MBhuggingface.co/bespokelabs/Bespoke-Nimble-9B-v2/resolve/4b8c04d…/tokenizer.json
  • decisioneeb65a2405c5 · 5 KB{"engine": "onnx", "family": "d3", "encoder": "", "layout": "d3-code-readout-v1", …}
  • calibration0f89e51fde90 · 133 B{"temperature": [1.0, 1.0, 1.0]}
  • license3d7ec11263ac · 10 KBDecision 3.0 (d3) by the vLLM Semantic Router contributors (https://huggingface.co/vllm-sr)

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.

Decision 3.0 (d3) readme and all models