Transformers changelog & release notes

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,…

New Model additions Nemotron 3 Diarization Nemotron 3 Diarization is an open-weight streaming speaker diarization model designed to determine "who spoke when" in real-world…

Release v5.17.0 New Model additions HYV4 Hy4-Preview is a 780B-parameter mixture-of-experts language model that activates 49B parameters per token. Each MoE layer holds 256…

Release v5.16.0 New Model additions Qwen4-Exp Qwen4-Exp builds on Qwen3.5's hybrid text and multimodal architecture with three key components: GatedResidual (GR), Qwen Sparse…

Release v5.16.1 This is a special release as we include GLM! (and a few small fixes) GLM-5.3-Flash GLM-5.3-Flash, the first natively multimodal model in the GLM-5 series. With…

Patch release v5.15.1 This patch most notably solves a few issues with DFlash and MTP candidate generators, as well as an issue where images could sometimes not be processed on…

Release v5.15.0 New Model additions Meta Muse Glimmer Muse Glimmer, released today, is Meta’s new multimodal model, especially designed for agentic use cases. Distilled from Muse…

Patch release v5.14.1 This patch solves a few issues which appeared when integrating Inkling model, most notably an issue affecting models using EncoderDecoderCache during…

Release v5.14.0 New Model additions Inkling (fresh from Thinking Machines): 975B total, 41B active Add Inkling model #47347 by @molbap @Cyrilvallez @eustlb and @zucchini-nlp…