GTE-MLM sparse embedding models now natively supported in Transformers v5
tomaarsen · x · 2026-11-20
Transformers maintainer tomaarsen announces native integration of the GTE-MLM sparse embedding model line, to be maintained across all future transformers v5. releases. The original repos require trustremotecode=True and no longer work with the latest transformers, so he built native copies (e.g. tomaarsen/gte-en-mlm-large-native, from Alibaba-NLP/gte-en-mlm-large; unchanged weights/tokenizer, requires transformers>=5.18.0).
They work out of the box via SparseEncoder("tomaarsen/gte-en-mlm-large-native") like bert-base-uncased, ready for finetuning, especially retrieval fine-tuning with sentencetransformers.SparseEncoder; three models released.
Related event: GTE-MLM Sparse Embedding Models Get Native Transformers Support(2 posts)→
More from coding & agent
- Developer uses Antigravity agent swarm to auto-build two full pinball games — AI_Andrew · 2026-11-20
- Ridges launches Ridgeline: label a GitHub issue, an agent fleet ships the PR — markjeffrey · 2026-11-20
- Claude drew an entire flyable game world with pure code — no images, no 3D models — prasenx · 2026-11-20
- Fixing mobile input auto-zoom: a Shadcn refinement workflow with Impeccable skills — bennash · 2026-11-20
- DeepSeek V4.1 Flash pushed from broken to 284+ t/s on RTX PRO 6000, +78.7% over vLLM — SergioPaniego · 2026-11-20
- After evaluating Forge for MTG, researcher writes his own engine for RL agents — petrusenko_max · 2026-11-20