| --- |
| license: apache-2.0 |
| base_model: jaredpalmer/kev-0.8b |
| library_name: onnxruntime |
| pipeline_tag: text-classification |
| tags: |
| - kev |
| - decision-model |
| - typesafe |
| - qwen3.5 |
| - onnx |
| - webgpu |
| --- |
| |
| # kev-0.8b-ONNX |
|
|
| [kev-0.8b](https://huggingface.co/jaredpalmer/kev-0.8b) (revision `9a45d25eb2ab761841196625383fa1dff0e56c1e`) by Jared Palmer, packaged for the browser by |
| [runonweb](https://runonweb.ai/models/classify) (`runonweb/classify`). |
|
|
| Kev is a Jev-style decision model: typed questions about one text (`noul` yes/no, `choice`, `score`) |
| answered with calibrated probabilities, no text generation. Requests follow TypeSafe's System One API. |
|
|
| ## What changed from the original |
|
|
| - The rank-16 LoRA is merged into `Qwen/Qwen3.5-0.8B-Base` (revision `dc7cdfe2ee4154fa7e30f5b51ca41bfa40174e68`) in fp32. |
| - The backbone is exported with the onnxruntime-genai builder without the LM head and MTP layer: the graph |
| returns `hidden_states` plus the recurrent/conv/KV cache, so the state is encoded once and each question |
| runs as its own row on that cache (Kev's row form). |
| - Weights are int4 (RTN, block 32) with the Gated DeltaNet projections and their MLPs in int8; activations fp32. ~735 MB. Needs the `LinearAttention` / `CausalConvWithState` contrib ops: ONNX Runtime Web's native WebGPU |
| build (`onnxruntime-web/webgpu`) on the GPU, `onnxruntime-web/wasm` on the CPU. |
| - The pointer head is `head.bin` (fp32: `q.weight`, `q.bias`, `k.weight`, `k.bias`); `kev.json` holds the |
| calibration temperature, delimiter token ids and cache layout. |
|
|
| On 318 questions from Kev's development suites, probabilities differ from the fp32 export by 0.028 on average; 16 answers change, none with a margin above 0.2 (accuracy 0.657 vs 0.664). The fp32 export of the same graph matches Kev's PyTorch fp32 path within 4e-5. |
| Recipe: `training/kev-onnx` in the runonweb repo. |
|
|
| ## Use |
|
|
| ```ts |
| import { Classifier } from 'runonweb/classify' |
| |
| const classifier = new Classifier({ model: 'midudev/kev-0.8b-ONNX' }) |
| const { answers } = await classifier.classify({ |
| state: 'I was charged twice. Please fix this ASAP.', |
| questions: { billing: { type: 'noul', instructions: 'Is this ticket about billing?' } }, |
| }) |
| ``` |
|
|
| ## License |
|
|
| Apache-2.0, like Kev and the Qwen3.5 base. Kev's training datasets have their own licenses; see the |
| [original model card](https://huggingface.co/jaredpalmer/kev-0.8b). |
|
|
