transformers v5.19.0 — Release v5.19.0
# Release v5.19.0 ## New Model additions ### EmbeddingGemma2 EmbeddingGemma 2 is a multimodal embedding model from Google built on the Gemma 4 architecture. It encodes text, images, audio, and video, individually or combined in one input, into a shared 768-dimensional vector space for cross-modal retrieval, semantic similarity, clustering, and classification. It uses Matryoshka Representation Learning, so embeddings can be truncated to 512, 256, or 128 dimensions. It also offers configurable visual and video token budgets, and unused vision or audio towers can be disabled at load time to save memory. **Links:** [Documentation](https://huggingface.co/docs/transformers/main/en/model_doc/embedding_gemma2) * Smthn smthn (#49364) by @vasqu in [#49364](https://github.com/huggingface/transformers/pull/49364) ## Breaking changes All MoE models whose routers compute logits now return them when , following the Qwen3-MoE pattern (a recorder on the base model, from the backbone, and a MoE causal LM output from the head), so code that relied on the previous outputs or their absence should…
Covered by 1 source
- GGitHub Releases↗Oct 6