Skip to content

kev:4b

4 TagsUpdated 4.2B params8192 contextEnglishApache-2.0by Jared Palmer

Qwen3.5-4B base, round 10, 0.669 on typed decisions. Best on a GPU.

4.2b
ollaya run kev:4b --preset triage "I was charged twice for my subscription this month and want a refund."

Details

  • graph137283895b84 · 14 MBonnx · kev · 4.2B · fp32
  • weightsdf547074dce7 · 5.3 GBhuggingface.co/Qwen/Qwen3.5-4B-Base/resolve/1001bb4…/model.safetensors-00001-of-00002.safetensors
  • weights590fbaac095d · 4.0 GBhuggingface.co/Qwen/Qwen3.5-4B-Base/resolve/1001bb4…/model.safetensors-00002-of-00002.safetensors
  • weights90e817356246 · 130 MBhuggingface.co/jaredpalmer/kev-4b/resolve/139fdd9…/adapter_model.safetensors
  • weightsdd633435998e · 5 MBhuggingface.co/jaredpalmer/kev-4b/resolve/139fdd9…/head.pt
  • tokenizer06b9509352d2 · 20 MBhuggingface.co/jaredpalmer/kev-4b/resolve/139fdd9…/tokenizer.json
  • decision79b66d83478d · 3 KB{"engine": "onnx", "family": "kev", "encoder": "", "layout": "kev-pointer-v1", …}
  • calibrationa51c52e256db · 252 B{"temperature": [2.406, 2.406, 2.406]}
  • license5ddbf0af0c82 · 10 KBKev by Jared Palmer (https://huggingface.co/jaredpalmer/kev-4b)

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.

Kev readme and all models