Model cards¶
Verified m0 models. Each card documents the adapter contract, the real download,
the measured evidence and the known limitations. Models that are not m0 have no
card on purpose: they are not part of the curated library yet.
| Model | Adapter | Variants (default *) | Pinned | Latency (CPU) | Evidence |
|---|---|---|---|---|---|
| GLiNER2.5 multi | gliner2 |
fp16* · 577 MB; fp32 · 1132 MB | 3de2c11f |
353 ms | 9/15 routing; same as local int8 |
| GLiNER2.5-Decide | gliner2-decide |
q4f16* · 524 MB | 18271032 |
912 ms | refund 0.944 (card example) |
| Laya (English) | laya |
q8* · 528 MB | cccc9a01 |
514 ms | torch parity: Δp ≤ 0.005 |
| Julia 1 | julia |
fp32* · 618 MB | 82a2fadf |
329 ms | 100/100 argmax; 8.5e-05 max logit error |
| OpenDecider nano | opendecider |
q8f16* · 469 MB; fp16 · 792 MB | 5137ae7b |
530 ms | official build; prompt ported from pinned code |
A * marks the default. To inspect sizes, hashes and exact commands, run
dtk models variants <id> or read Variants and quantization.
Latencies above are the historical admission measurements. Reproducible post-warmup measurements and the exact command are in BENCH.md.
What a card must contain¶
- Status and adapter (the model contract).
- Every catalogued variant: repo, files, quantization, download size and role.
- Measured evidence: latency on CPU, parity/accuracy against a named baseline.
- Known limitations (language, export layout, quantization, benchmark scope).
- A runnable usage example.
- Provenance of the export.
- The pinned revision and SHA256 per file, plus the verify/bench command.