Skip to content

d3:latest

6 TagsUpdated 4B params8192 contextEnglishApache-2.0by vLLM Semantic Router

Same as d3:mini.

4b
ollaya run d3 --preset triage "I was charged twice for my subscription this month and want a refund."

Details

  • graph1ba29558a7d5 · 12 MBonnx · d3 · 4B · fp32
  • weights60621cb8c3f9 · 5.0 GBhuggingface.co/vllm-sr/d3-mini/resolve/bd0090d…/model-00001-of-00002.safetensors
  • weights6189569fbe92 · 4.1 GBhuggingface.co/vllm-sr/d3-mini/resolve/bd0090d…/model-00002-of-00002.safetensors
  • weightsd570665c1da7 · 3 MBhuggingface.co/vllm-sr/d3-mini/resolve/bd0090d…/readout.safetensors
  • tokenizer06b9509352d2 · 20 MBhuggingface.co/bespokelabs/Bespoke-Nimble-9B-v2/resolve/4b8c04d…/tokenizer.json
  • decision962d8401c26f · 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