QVAC-18487 feat[mod]: sync sdk model registry to bergamot base-memory and drop deprecated marian opus#1903
Merged
opaninakuffo merged 3 commits intoMay 5, 2026
Conversation
…eprecated marian opus
- Bumps BERGAMOT_EN_IT and BERGAMOT_ES_EN to the base-memory variant at
bergamot-{enit,esen}/2026-04-28/. Fixes leading "- " hallucinations on
short inputs and en->it quality regression (registry seed updated in
tetherto#1785, synced to DHT 2026-05-05).
- Drops 32 deprecated Marian Opus entries (NMT_Q0F16*, NMT_Q4_0*)
auto-deprecated by tetherto#1680.
- Auto-generated by `bun update-models`.
NamelsKing
approved these changes
May 5, 2026
Contributor
QVAC E2E —
|
Contributor
Contributor
Contributor
Contributor
Victor-Rodzko
approved these changes
May 5, 2026
Contributor
Author
|
review |
Contributor
Tier-based Approval Status |
Contributor
Author
|
review |
opaninakuffo
added a commit
to opaninakuffo/qvac
that referenced
this pull request
May 5, 2026
…eprecated marian opus (tetherto#1903) - Bumps BERGAMOT_EN_IT and BERGAMOT_ES_EN to the base-memory variant at bergamot-{enit,esen}/2026-04-28/. Fixes leading "- " hallucinations on short inputs and en->it quality regression (registry seed updated in tetherto#1785, synced to DHT 2026-05-05). - Drops 32 deprecated Marian Opus entries (NMT_Q0F16*, NMT_Q4_0*) auto-deprecated by tetherto#1680. - Auto-generated by `bun update-models`.
This was referenced May 5, 2026
tamer-hassan-tether
pushed a commit
that referenced
this pull request
May 6, 2026
…eprecated marian opus (#1903) - Bumps BERGAMOT_EN_IT and BERGAMOT_ES_EN to the base-memory variant at bergamot-{enit,esen}/2026-04-28/. Fixes leading "- " hallucinations on short inputs and en->it quality regression (registry seed updated in #1785, synced to DHT 2026-05-05). - Drops 32 deprecated Marian Opus entries (NMT_Q0F16*, NMT_Q4_0*) auto-deprecated by #1680. - Auto-generated by `bun update-models`.
tamer-hassan-tether
pushed a commit
that referenced
this pull request
May 6, 2026
…eprecated marian opus (#1903) - Bumps BERGAMOT_EN_IT and BERGAMOT_ES_EN to the base-memory variant at bergamot-{enit,esen}/2026-04-28/. Fixes leading "- " hallucinations on short inputs and en->it quality regression (registry seed updated in #1785, synced to DHT 2026-05-05). - Drops 32 deprecated Marian Opus entries (NMT_Q0F16*, NMT_Q4_0*) auto-deprecated by #1680. - Auto-generated by `bun update-models`.
opaninakuffo
added a commit
that referenced
this pull request
May 6, 2026
* QVAC-18420 fix[mod]: Bergamot vocab re-downloaded on every loadModel for shared-vocab pairs (#1892) * QVAC-18420 fix[mod]: Bergamot vocab re-downloaded on every loadModel for shared-vocab pairs - Dedup preserves registry entries referenced as companion files in any companion set, so shared-vocab blobs (identical sha256 under two paths) keep their standalone RegistryItem. This adds back 7 previously-dropped BERGAMOT_<pair>_VOCAB entries (FR_EN, EN_DE, EN_CS, ET_EN, FI_EN, PL_EN, PT_EN) and restores correct expectedSize/sha lookups for the Bergamot plugin's separate vocab resolve. - For registry:// Bergamot loads with auto-derived vocabs (non-pivot and pivot), skip the separate per-vocab resolveModelPath entirely. The companion-set download already colocates vocabs under sets/<setKey>/ and createModel derives those paths via deriveColocatedBergamotVocabPaths — no redundant flat-cache download, no dedup-hole exposure. * QVAC-18420 test: cover Bergamot vocab resolver + extract pure helpers Reviewer ask on PR #1892: lock the Fix-C registry-source vocab optimization behind unit tests so the contract doesn't drift. - Extract resolveBergamotVocab and its derivation helpers into resolve-vocab.ts. The plugin module imports @qvac/translation-nmtcpp at module-load time (Bare-only native addon), so the helpers were not importable from a bun-driven test runner. The new module has zero native deps; plugin.ts re-imports from it. - Add test/unit/nmtcpp-resolve-vocab.test.ts covering: - registry:// + auto-derived vocabs (non-pivot) → ctx.resolveModelPath is never called and no vocab artifacts are emitted - registry:// + auto-derived vocabs (pivot) → exactly one resolveModelPath call (the pivot model itself), no vocab artifacts - registry:// + user-supplied srcVocabSrc OR dstVocabSrc → optimization is skipped and full per-vocab resolution runs (sanity: keeps the optimization narrow) - pear:// source still resolves vocabs explicitly (companion-set semantics don't apply) - mixed registry/pear pivot triggers full resolution path - unsupported sources raise ModelLoadFailedError - pure derivation helpers (buildBergamotVocabSources, deriveBergamotVocabSources, deriveBergamotRegistryVocabSources) for both shared-vocab and CJK split-vocab pairs --------- Co-authored-by: Opanin Akuffo <46673050+opaninakuffo@users.noreply.github.com> * QVAC-17324 feat[api]: add harmony tool-call dialect (gpt-oss) (#1878) * chore: bump @qvac/llm-llamacpp to 0.17.2 for harmony EOG fix - Picks up #1812 which stops the addon from suppressing the `<|call|>` end-of-generation token, unblocking harmony tool-call parsing on the SDK side. * feat: expose toolDialect override and add harmony to the dialect enum * feat: add harmony tool-call parser for gpt-oss models * feat: stream harmony frames and decouple dialect from tool-call activation * test: add harmony unit coverage for parser and normalizer * chore: consolidate tool examples under examples/tools/ * doc: clarify emitThinking capture-gating contract * chore: remove conflict markers * feat[mod]: sync sdk model registry to bergamot base-memory and drop deprecated marian opus (#1903) - Bumps BERGAMOT_EN_IT and BERGAMOT_ES_EN to the base-memory variant at bergamot-{enit,esen}/2026-04-28/. Fixes leading "- " hallucinations on short inputs and en->it quality regression (registry seed updated in #1785, synced to DHT 2026-05-05). - Drops 32 deprecated Marian Opus entries (NMT_Q0F16*, NMT_Q4_0*) auto-deprecated by #1680. - Auto-generated by `bun update-models`. * chore[skiplog]: release sdk 0.10.1 --------- Co-authored-by: Simon Iribarren <simon.ig13@gmail.com>
Merged
7 tasks
Proletter
pushed a commit
that referenced
this pull request
May 24, 2026
…eprecated marian opus (#1903) - Bumps BERGAMOT_EN_IT and BERGAMOT_ES_EN to the base-memory variant at bergamot-{enit,esen}/2026-04-28/. Fixes leading "- " hallucinations on short inputs and en->it quality regression (registry seed updated in #1785, synced to DHT 2026-05-05). - Drops 32 deprecated Marian Opus entries (NMT_Q0F16*, NMT_Q4_0*) auto-deprecated by #1680. - Auto-generated by `bun update-models`.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Note: be concise and prefer bullet points.
🎯 What problem does this PR solve?
packages/sdk/models/registry/models.tspinnedBERGAMOT_EN_ITandBERGAMOT_ES_ENto the buggytinyBergamot variant atbergamot-{enit,esen}/2025-12-18/. Caused leading"- "hallucinations on short inputs and en→it quality regression (~3 ppchrF++drop on[Bergamot] [CPU], ~33 pp on[Pivot es→en→it] [CPU]).📝 How does it solve it?
bun update-modelsagainst the staging registry, which now serves thebase-memoryBergamot bytes (seeded by QVAC-17892 fix[ci]: use refreshed base-memory bergamot models for desktop integration tests #1785, synced to DHT 2026-05-05).2025-12-18/Bergamot entries and the 32 Marian Opus entries from QVAC-14576 chore: remove Opus model entries from registry server #1680.🧪 How was it tested?
bun update-models --checkfrompackages/sdkreports clean ("Models are up to date") after the regen.BERGAMOT_EN_ITandBERGAMOT_ES_ENexpectedSizeflipped 17.1MB → 30.1MB, confirming thetiny→base-memoryswitch.bergamot-{enit,esen}/2026-04-28/...(matchesmodels.prod.jsonpost-QVAC-17892 fix[ci]: use refreshed base-memory bergamot models for desktop integration tests #1785).📦 Models
Removed models