transformers v5.20.0 — Release v5.20.0

# Release v5.20.0 ## New Model additions ### Muse Spark Open Muse Spark Open is a multimodal mixture-of-experts model from Meta that takes text, images, audio, and video as input and generates text. It has 816B total parameters (42B active per token) and a context window of up to 1,048,576 tokens shared across modalities. It is trained for agentic coding tasks such as multi-file editing, debugging, and tool use. Checkpoints are available in BF16 and NVFP4 formats. **Links:** [Documentation](https://huggingface.co/docs/transformers/main/en/model_doc/muse_spark) | [Blog Post](http://hf.co/blog/meta-muse-spark-open) * Add Muse Spark Open (#49644) by @guarin in [#49644](https://github.com/huggingface/transformers/pull/49644) ### Ling 3.0 Ling 3.0 Flash is a hybrid Mixture-of-Experts language model from InclusionAI. Its decoder groups five Kimi Delta Attention (KDA) layers with one Multi-head Latent Attention (MLA) layer. The MLA blocks use interleaved rotary embeddings and a head-wise output gate, and the feed-forward blocks combine routed and shared experts. It is natively supported in Transformers as…