Transformers v5.20.0 发布:新增多个模型支持
原标题:Release v5.20.0
AI 摘要
Hugging Face Transformers 发布 v5.20.0,新增多个模型支持,包括 Meta 的多模态 MoE 模型 Muse Spark Open、InclusionAI 的 Ling 3.0 Flash、Aleph Alpha 的 Kolibri 1、OpenBMB 的 MiniCPM-V 4.7、百度的 UnlimitedOcr、UltraBERT 系列以及 MOSS-Transcribe-Diarize。该版本还包含破坏性变更:移除 cache_utils.py 中已弃用的检查和方法,并提示 EP 推理速度出现回退。
正文节选
# Release v5.20.0 ## New Model additions ### Muse Spark Open <img width="2400" height="1296" alt="image" src="https://github.com/user-attachments/assets/bf34ea27-0edf-4ded-ba6f-905b04096126" /> 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 cod