Transformers · Release: v5.21.0

# Release v5.21.0 ## New Model additions ### MiniCPM-OCR MiniCPM-OCR is a document-understanding model from OpenBMB's MiniCPM-V family. It keeps the MiniCPM-V 4.6 architecture, which pairs a SigLIP vision encoder and a window-attention merger with a Qwen3.5 language model. It is specialized for reading text-dense images such as scanned pages, screenshots, receipts and tables. **Links:** [Documentation](https://huggingface.co/docs/transformers/main/en/model_doc/minicpm_ocr) | [Paper](https://huggingface.co/papers/2509.18154) * Feat test (#49920) by @guarin in [#49920](https://github.com/huggingface/transformers/pull/49920) ### Flint Flint is Recursive's mixture-of-experts language model. Compared to a standard SwiGLU MoE transformer such as Qwen3-MoE, it uses hybrid attention (sliding-windo

1 个独立来源 · 1 篇报道切换最早在前 ↕

2026-10-27

Transformers releases02:17

版本：v5.21.0

# 发布版本 v5.21.0 ## 新增模型 ### MiniCPM-OCR MiniCPM-OCR 是 OpenBMB 的 MiniCPM-V 系列中的一款文档理解模型。它沿用了 MiniCPM-V 4.6 的架构，即由 SigLIP 视觉编码器与窗口注意力融合模块搭配 Qwen3.5 语言模型组成。该模型专为解析文本密集的图像而设计，例如扫描页、截图、收据和表格等。 **链接：** [文档](https://huggingface.co/docs/transformers/main/en/model_doc/minicpm_ocr) | [论文](https://huggingface.co/papers/2509.18154) * @guarin 在 [#49920](https://github.com/huggingface/transformers/pull/49920) 中提交的特性测试 (#49920) ### Flint Flint 是 Recursive 公司的专家混合语言模型。与 Qwen3-MoE 等标准的 SwiGLU MoE 变换器相比，它采用了混合注意力机制（滑动窗口…

事件进展与其他报道