Sentence Transformers Adds Training-Free Model Merging
Sentence Transformers maintainer tomaarsen introduced a new feature that merges compatible embedding model checkpoints without retraining, built on Arcee, demonstrated by blending two MiniLM models with 60/40 weighting.
2026-10-29 ~ 2026-10-29 · 2 related posts
- Sentence Transformers adds model merging: 60/40 weighted blend of two MiniLM checkpoints — tomaarsen · 2026-10-29
- Sentence Transformers adds training-free model merging via mergekit, with Linear, SLERP and TIES — tomaarsen · 2026-10-29