Roadmap (not in the catalog)¶
The catalog only contains models that are runnable today (m0). The entries
below are researched but not available through the toolkit: they have no ONNX
export, no verified parity, a broken export, or an adapter still to be written.
They are deliberately absent from CATALOG, dtk models list and /v1/models.
| id | status | reason |
|---|---|---|
gliner2.5-multi-decide |
planned | No compatible export of the fine-tune; only the base multi-v1 export is verified |
laya-multilingual |
planned | No split multilingual ONNX export published (existing ones are fused single-file layouts) |
intern-decision-0.8b |
planned | Split embed/decoder/projection export; needs the upstream prompt compiler; parityVerified: false |
d3-lite |
phase2 | No ONNX published; conversion from the original weights planned |
kev-0.8b |
phase2 | No ONNX published; conversion planned |
sieve-0.8b |
phase2 | No ONNX published; conversion planned |
strands-decider-2b |
phase2 | No ONNX published; conversion planned |
thx-01 |
phase2 | No ONNX published; conversion planned |
jevk5-lite |
waitlist | Export references external .onnx.data files that are not published |
bosun-0.6b |
waitlist | No ONNX yet |
d3-edge |
waitlist | No ONNX yet |
tev1-0.8b |
waitlist | License not declared on the model card |
d1-omni-600m |
waitlist | LFM Open License; needs review |
bekko-400m |
waitlist | License pending |
How a model moves into the catalog¶
- A real, runnable ONNX export exists on the Hub.
- Its contract is understood and an adapter runs it (written only from the real files).
- Parity against the original is measured on a fixed sample.
- License is clean and CPU latency is measured.
- A model card is written; the variant carries
verified_at,latency_ms_p50andparity.
Conversion work (safetensors → ONNX, quantization, manifests) is a separate project planned for the next phase.