model2vec

v0.8.2 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 5d Model Serving & MLOps

✓ No known CVEs patched

✓ No known CVEs patched in this version

Topics

ai embeddings machine-learning model2vec nlp python

+2 more

sentence-transformers word-embeddings

Summary

AI summary

Updates fix, feat, and chore across a mixed release.

Type	Severity	Summary	CVE
Feature
Feature	Low	Adds frozen‑weights option to training. Adds frozen‑weights option to training. Source: llm_adapter@2026-05-29 Confidence: high	—
Feature	Low	Adds trusted publisher support. Adds trusted publisher support. Source: llm_adapter@2026-05-29 Confidence: high	—
Feature	Low	Converts distill output to float. Converts distill output to float. Source: llm_adapter@2026-05-29 Confidence: high	—
Bugfix
Bugfix	Medium	Fixes multiword token handling bug. Fixes multiword token handling bug. Source: llm_adapter@2026-05-29 Confidence: high	—
Bugfix	Medium	Fixes incorrect added token causing issues as multiword. Fixes incorrect added token causing issues as multiword. Source: llm_adapter@2026-05-29 Confidence: high	—
Bugfix	Medium	Fixes weight assignment for non‑quantized models. Fixes weight assignment for non‑quantized models. Source: llm_adapter@2026-05-29 Confidence: high	—
Bugfix	Medium	Fixes weight setting when w is initialized. Fixes weight setting when w is initialized. Source: llm_adapter@2026-05-29 Confidence: low	—
Bugfix	Low	Fixes small typing issue. Fixes small typing issue. Source: llm_adapter@2026-05-29 Confidence: high	—
Bugfix	Low	Correctly sets weights when variable w is initialized. Correctly sets weights when variable w is initialized. Source: granite4.1:30b@2026-05-29-audit Confidence: low	—

Full changelog

fix: multiword broken by @stephantul in https://github.com/MinishLab/model2vec/pull/317
feat: refactor training by @stephantul in https://github.com/MinishLab/model2vec/pull/316
fix: upgrade skeletoken by @stephantul in https://github.com/MinishLab/model2vec/pull/318
fix: Incorrect added token can cause issues when adding token as multiword token by @stephantul in https://github.com/MinishLab/model2vec/pull/319
fix: don't set weights for non-quantized models by @stephantul in https://github.com/MinishLab/model2vec/pull/321
fix: correctly set weights when w is initialized by @stephantul in https://github.com/MinishLab/model2vec/pull/322
feat: convert output to float in distill by @stephantul in https://github.com/MinishLab/model2vec/pull/320
clean up post-processing code by @stephantul in https://github.com/MinishLab/model2vec/pull/323
chore: fix pre-commit by @stephantul in https://github.com/MinishLab/model2vec/pull/326
chore: add exclude-newer by @stephantul in https://github.com/MinishLab/model2vec/pull/328
feat: add frozen-weights option to training by @stephantul in https://github.com/MinishLab/model2vec/pull/327
fix: small typing issue by @stephantul in https://github.com/MinishLab/model2vec/pull/329
chore: Update email by @Pringled in https://github.com/MinishLab/model2vec/pull/331
feat: add trusted publisher by @stephantul in https://github.com/MinishLab/model2vec/pull/332

Full Changelog: https://github.com/MinishLab/model2vec/compare/v0.8.1...v0.8.2

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track model2vec

Get notified when new releases ship.

About model2vec