Sven-0.6B — svensk System One-beslutsmodell
Sven answers typed questions (
choice/score/noul) about Swedish or English text with calibrated probabilities in one forward pass. No text generation, no type errors. It is a delta fine-tune of Kev-0.6B — the open, Apache-2.0 Jev-family member built by Jared Palmer — adapted to Swedish by Birger Moell / AI Sweden.
Try it + full stack
| link | note | |
|---|---|---|
| 🖥️ In-browser demo (no server, no keys) | birgermoell/sven-space | static Space; ONNX q4/fp16 in WebGPU→WASM; first load ~0.9 GB |
| 🧮 Browser weights (ONNX) | birgermoell/sven-web | merged LoRA + pointer head; measured drift vs fp32: q4 ±0.024, fp16 ±0.008 |
| 📊 Training dataset + provenance | birgermoell/sven-data | 5k translated records + 36 hand-written Swedish seeds + audit TSV |
| 🔀 Local LLM-router recipe | repo: swedish-jev (git) — copy under router/ |
Sven first, Ollama when generation is needed; calibrated gates + JSONL decision log |
| 🤝 Upstream (and credit) | jaredpalmer/kev | vendored Apache-2.0; deviations documented in VENDORED.md |
Alla artefakter samlas i Hub-kollektionen "Sven — svensk System One".
Status: v0.1 (published), what changes next
Färdigt i v0.1: svensk/engelsk choice-score-noul med kalibrerade probabilities; tre publicerade utvärderingar nedan; ONNX-export med kvantparitet; demo + router.
Pågår / väntar (uppdateras här efterhand): v0.2 med 4B-backbone för score-frågorna, svenska router-proband-poster ((ticketlike/needs_llm-utforskningar är därför konservativa i demo-router:n), ev. QDQ-int4 för WebGPU-kärnfellet (orkar falla tillbaka till WASM, samma siffror).
Intended use
System One requests in Swedish or English: kundtjänst-routing, mejltriage, phishing/bedrägeri and
prompt-injection-gardrails, incident-klassning, urgency/frustration-rubriker — the same mixed
distribution as the upstream Kev recipe (banking77, MNLI, SST-5, BoolQ, …), machine-translated to
Swedish plus hand-written Swedish seed records. Serve with the vendored Kev server:
python -m kev.serve --run <this repo> --port 8009 (TypeSafe-compatible /v1/systemone).
Results
Evaluated fp32 (MPS), frozen upstream dev partitions; Swedish split held out per record.
| eval | accuracy | Brier | ECE | selective acc @50% cov | n (rejected) |
|---|---|---|---|---|---|
| Swedish held-out | 0.745 | 0.331 | 0.079 | 0.947 | 400 (8) |
| └ choice | 0.751 | — | — | — | — |
| └ noul (yes/no) | 0.863 | 0.225 | 0.075 | 0.986 | — |
| └ score (0–4 rubrics) | 0.520 | 0.556 | 0.099 | — | — |
| English in-distribution (decision-v7 dev) | 0.794 | 0.299 | 0.090 | 0.959 | 1,204 |
| English out-of-domain (transfer-v4 dev) | 0.623 | 0.536 | 0.146 | 0.726 | 764 |
Upstream reference, same suites (Kev-0.6B, English): 0.801 in-distribution / 0.620 out-of-domain acc; Brier 0.266 / 0.483 (locked test). Sven retires < 1 point of upstream English accuracy with the Swedish delta applied — the fine-tune does not wash out the base recipe.
Rejected records (state/branch over Kev's serving context, e.g. 77-option routing with long Swedish criteria) count as wrong; 8/400 = 2% on the Swedish split.
Training
- Base:
Qwen/Qwen3-0.6B-Base@da87bfb6…(Apache-2.0), warm-started fromjaredpalmer/kev-0.6b(392 LoRA tensors + pointer head), delta LR 2e-5, 2 epochs, batch 1 × grad-accum 8, fp32 master weights, cross-entropy on the option distribution (upstream protocol; no Jev outputs used). - Data: 5,000 EN→SV machine-translated records (stratified sample of upstream
decision-v7train; MT:Helsinki-NLP/opus-mt-en-sv, unique-string cache; option keys kept English with Swedish criteria text) + 36 hand-written Swedish seed records (Swedish option keys; routing, phishing, incident, GDPR and prompt-injection domains) + 200 English replay records from the upstream suite to prevent recipe drift. - Provenance:
sven-datadataset (train/held-out split sha256 of suite, per-source counts, MT audit sample of 30 EN→SV pairs).
Data & licenses
Everything open: Apache-2.0 (code + weights) per upstream Kev; Qwen3-0.6B-Base Apache-2.0;
OPUS-MT translator open. Translated training data is redistributed for research with per-source
documentation in DATA_LICENSES.md (Banking77 CC-BY-4.0, BoolQ/MNLI/DBpedia CC-BY-SA, etc.);
dataset release ships provenance so stricter per-source terms can be traced. Hand-written Swedish
seeds and this card: CC-BY-4.0 / Apache-2.0 respectively.
Known limits
- Score questions are the weak spot (0.52 on translated 0–4 rubrics): the length of Swedish criteria plus 0.6B capacity — not data volume — is the binding constraint (upstream notes the same physics). The documented fix is the 4B backbone (planned v0.2).
- MT-translated labels inherit MT noise; review
audit_sv.tsv(sven-data) for a human-checked sample. One long-review record showed visible MT truncation. - Most translated records keep English option keys (
fakturering-style keys only in seeds), so Swedish option-key handling is narrower than the state/question coverage. - Probabilities are advisory out-of-domain (ECE 0.15 transfer) — gate automation on confidence (at ≥0.9 confidence the Swedish split lands ~0.90 accuracy on the covered share).
- Same architecture caveats as upstream: option-order sensitivity remains; questions cannot read each other by design; latency unchanged from Kev-0.6B (0.12 s / five questions on M-series).
Use
from typesafe import TypeSafeClient
client = TypeSafeClient(api_key="local", base_url="http://127.0.0.1:8009", model="sven-latest")
KEV_DTYPE=bf16 python -m kev.serve --run <HF repo or local run dir> --port 8009
License
Apache-2.0 for the adapter and head (upstream Kev license). Base model Apache-2.0 (Qwen3). Built with the vendored Kev codebase (see VENDORED.md).