kev.js weights

Browser-ready exports of Kev, Jared Palmer's family of small decision models. They answer yes/no, multiple-choice and rating questions with calibrated probabilities, and run in a browser on WebGPU through @ai-ecoverse/kev.js. This repo holds only converted weights: no training, evaluation or model design here is ours.

import * as ort from "onnxruntime-web/webgpu";
import { loadKev } from "@ai-ecoverse/kev.js";

const kev = await loadKev("https://huggingface.co/ai-ecoverse/kev.js/resolve/main/kev-0.8b", { ort, variant: "q8f32" });
const res = await kev.systemOne({
  state: "I was charged twice. Please fix this ASAP.",
  questions: { billing: { type: "noul", instructions: "Is this ticket about billing?" } },
});

Contents

Folder	Variant	Download	Base	Source checkpoint
kev-0.8b	q8f32	0.82 GB	Qwen/Qwen3.5-0.8B-Base	jaredpalmer/kev-0.8b@225679690cdd1de6fceb1258b1bddf61c493cee9
kev-0.8b	q8	0.79 GB	Qwen/Qwen3.5-0.8B-Base	jaredpalmer/kev-0.8b@225679690cdd1de6fceb1258b1bddf61c493cee9
kev-4b	q8f32	4.67 GB	Qwen/Qwen3.5-4B-Base	jaredpalmer/kev-4b@4bc64c6b4c4881148661ffb823ce21fcfdc79a0e
kev-9b	q8f32	8.83 GB	Qwen/Qwen3.5-9B-Base	jaredpalmer/kev-9b@442e597d71840506c326c8c2f5eedd42aeac7bbd

Every bundle is int8 weights with fp32 activations, split into 32 MB files so any CDN or proxy can serve them. manifest.json lists the files, their sizes, the tokenizer and the pointer head, plus the measured deviation from the original fp32 PyTorch model on a fixture set.

Provenance and licenses

• Models and training: jaredpalmer/kev (Apache-2.0). Source checkpoints: jaredpalmer/kev-0.8b@225679690cdd1de6fceb1258b1bddf61c493cee9, jaredpalmer/kev-4b@4bc64c6b4c4881148661ffb823ce21fcfdc79a0e, jaredpalmer/kev-9b@442e597d71840506c326c8c2f5eedd42aeac7bbd.
• Base models: Qwen3.5 (Apache-2.0).
• Architecture described in Jev's Architecture Unmasked. The API shapes follow TypeSafe's System One; Jev is TypeSafe's hosted model and is not affiliated with this repo.
• Conversion: LoRA merged in fp32, exported with the onnxruntime-genai model builder without the LM head, embeddings quantized to int8 per row. Details in the kev.js README.