Add bilingual project flow covers

.gitattributes

@@ -38,3 +38,5 @@ head.f32 filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
 bit-jev-autodl-case.en.png filter=lfs diff=lfs merge=lfs -text
 bit-jev-autodl-case.zh-CN.png filter=lfs diff=lfs merge=lfs -text
+project-cover.en.png filter=lfs diff=lfs merge=lfs -text
+project-cover.zh-CN.png filter=lfs diff=lfs merge=lfs -text

README.en.md

@@ -15,6 +15,10 @@ tags:
 
 [中文模型卡](README.md) · [Source repository](https://github.com/Zeaulo/bit-jev)
 
+![bit-jev training, distillation, and I2_S CPU inference flow](project-cover.en.png)
+
+The ternary symbols represent quantized BitLinear weights; training and inference are separate flows.
+
 > This repository provides the I2_S CPU inference package for bit-jev. The checkpoint was trained on a multi-source decision dataset that includes Yelp review records. A request for permission covering derivative weights and metrics has been sent to Yelp; as of 2026-09-28, no written reply has been received. The Apache-2.0 license for the source repository does not automatically apply to this checkpoint.
 
 ## Model summary

README.md

@@ -15,6 +15,10 @@ tags:
 
 [English model card](README.en.md) · [源码仓库](https://github.com/Zeaulo/bit-jev)
 
+![bit-jev 训练、蒸馏与 I2_S CPU 推理流程](project-cover.zh-CN.png)
+
+图中三值符号只代表量化 BitLinear 权重；训练与推理是分开的流程。
+
 > 本仓库提供 bit-jev 的 I2_S CPU 推理模型包。权重来自包含 Yelp 评论数据的多源决策训练集。Yelp 权利方许可申请已发出，截至 2026-09-28 尚未收到书面答复。本模型卡公开说明来源与限制；项目代码仓库的 Apache-2.0 许可证不自动适用于此检查点。
 
 ## 模型简介