Update bilingual local web guides and flow figures

README.en.md

@@ -23,11 +23,12 @@ The bilingual test page lets you edit a customer support scenario and inspect th
 On Windows x64 with Python 3.11/3.12, install the current release with the interpreter that will run inference, then check the distribution version and import path:
 
 ```bash
-python -m pip install --upgrade --no-cache-dir bit-jev==0.12.10 -i https://pypi.org/simple
+pip install bit-jev -i https://pypi.org/simple --upgrade
+python -m bit_jev.demo
 python -c "from importlib.metadata import version; import bit_jev; print(version('bit-jev'), bit_jev.__file__)"
 ```
 
-The version should be `0.12.10`, and the import path should point into the active environment's `site-packages/bit_jev`. Then run the Python example below, which does not depend on the `bit-jev-demo` console script being on PATH. The first model load downloads roughly 1.19 GB; later runs reuse the cache. The default first tries Hugging Face and falls back to ModelScope if the connection fails. Use `source="modelscope"` to select ModelScope directly. See the [install guide](https://github.com/Zeaulo/bit-jev/blob/main/docs/GGUF_PACKAGE.md) for stale mirrors and mixed environments.
+The version should be `0.13.10`, and the import path should point into the active environment's `site-packages/bit_jev`. The second command opens a local Choice, Noul, and Score page; the first submitted question downloads and loads roughly 1.19 GB, and later requests reuse the model. Add `--source modelscope` to choose ModelScope directly, `--device gpu` for Vulkan, or `--once` for the former one-shot JSON output. The Python API example below remains available. See the [install guide](https://github.com/Zeaulo/bit-jev/blob/main/docs/GGUF_PACKAGE.md) for stale mirrors and mixed environments.
 
 ![bit-jev training, distillation, quantization, and CPU/Vulkan inference](project-flow.en.png)
 
@@ -72,7 +73,7 @@ This release contains the I2_S artifacts for the native CPU runner, matching tok
 
 ## Inference
 
-Install the Python package. On Windows x64 with an AVX2 CPU, the bit-jev 0.12.10 wheel includes precompiled CPU and Vulkan GPU runners. For `device="cpu"` or `device="gpu"`, inference needs no Git, CMake, compiler, or Vulkan SDK. Vulkan needs a compatible graphics driver that supplies `vulkan-1.dll`. The roughly 1.19 GB model still downloads on first use. Other platforms and CUDA build from pinned source and require Git, CMake 3.28+, and a C++17 compiler; CUDA needs the CUDA Toolkit.
+Install the Python package. On Windows x64 with an AVX2 CPU, the bit-jev 0.13.10 wheel includes precompiled CPU and Vulkan GPU runners. For `device="cpu"` or `device="gpu"`, inference needs no Git, CMake, compiler, or Vulkan SDK. Vulkan needs a compatible graphics driver that supplies `vulkan-1.dll`. The roughly 1.19 GB model still downloads on first use. Other platforms and CUDA build from pinned source and require Git, CMake 3.28+, and a C++17 compiler; CUDA needs the CUDA Toolkit.
 
 ```python
 from bit_jev.gguf import BitJev

README.md

@@ -23,11 +23,12 @@ tags:
 在运行推理的同一个 Python 3.11/3.12 环境中安装并核对版本：
 
 ```bash
-python -m pip install --upgrade --no-cache-dir bit-jev==0.12.10 -i https://pypi.org/simple
+pip install bit-jev -i https://pypi.org/simple --upgrade
+python -m bit_jev.demo
 python -c "from importlib.metadata import version; import bit_jev; print(version('bit-jev'), bit_jev.__file__)"
 ```
 
-版本应为 `0.12.10`，导入路径应指向当前环境的 `site-packages/bit_jev`。然后直接运行下方的 Python 示例；无需依赖 `bit-jev-demo` 命令的 PATH。首次加载会下载约 1.19 GB 模型，后续复用缓存。默认先尝试 Hugging Face，连接失败时回退 ModelScope；国内网络可在 `from_pretrained()` 中传入 `source="modelscope"`。镜像版本滞后及环境混用的处理见[安装指南](https://github.com/Zeaulo/bit-jev/blob/main/docs/GGUF_PACKAGE.zh-CN.md)。
+版本应为 `0.13.10`，导入路径应指向当前环境的 `site-packages/bit_jev`。第二条命令会在本机打开与在线测试同源的 Choice、Noul、Score 页面；首次提交才下载约 1.19 GB 模型。需要从 ModelScope 直接下载时可加 `--source modelscope`，使用 Vulkan 可加 `--device gpu`，旧式单题 JSON 可加 `--once`。下方仍保留完整 Python API 示例。镜像版本滞后及环境混用的处理见[安装指南](https://github.com/Zeaulo/bit-jev/blob/main/docs/GGUF_PACKAGE.zh-CN.md)。
 
 ![bit-jev 训练、蒸馏、量化与 CPU/Vulkan 推理流程](project-flow.zh-CN.png)
 
@@ -74,7 +75,7 @@ I2_S GGUF + float32 指针头
 
 ## 推理示例
 
-推荐使用 pip 包。Windows x64 且 CPU 支持 AVX2 时，bit-jev 0.12.10 wheel 已携带 CPU 与 Vulkan GPU 原生 runner；首次加载会按需下载约 1.19 GB 的模型。使用 `device="cpu"` 或 `device="gpu"` 推理无需 Git、CMake、C++ 编译器或 Vulkan SDK；Vulkan GPU 需要显卡驱动提供 `vulkan-1.dll`。其他系统和 CUDA 后端按需从固定源码构建，需要 Git、CMake 3.28+ 与 C++17 编译器；CUDA 构建还需要 CUDA Toolkit。
+推荐使用 pip 包。Windows x64 且 CPU 支持 AVX2 时，bit-jev 0.13.10 wheel 已携带 CPU 与 Vulkan GPU 原生 runner；首次加载会按需下载约 1.19 GB 的模型。使用 `device="cpu"` 或 `device="gpu"` 推理无需 Git、CMake、C++ 编译器或 Vulkan SDK；Vulkan GPU 需要显卡驱动提供 `vulkan-1.dll`。其他系统和 CUDA 后端按需从固定源码构建，需要 Git、CMake 3.28+ 与 C++17 编译器；CUDA 构建还需要 CUDA Toolkit。
 
 ```python
 from bit_jev.gguf import BitJev

README.zh-CN.md

@@ -23,11 +23,12 @@ tags:
 在运行推理的同一个 Python 3.11/3.12 环境中安装并核对版本：
 
 ```bash
-python -m pip install --upgrade --no-cache-dir bit-jev==0.12.10 -i https://pypi.org/simple
+pip install bit-jev -i https://pypi.org/simple --upgrade
+python -m bit_jev.demo
 python -c "from importlib.metadata import version; import bit_jev; print(version('bit-jev'), bit_jev.__file__)"
 ```
 
-版本应为 `0.12.10`，导入路径应指向当前环境的 `site-packages/bit_jev`。然后直接运行下方的 Python 示例；无需依赖 `bit-jev-demo` 命令的 PATH。首次加载会下载约 1.19 GB 模型，后续复用缓存。默认先尝试 Hugging Face，连接失败时回退 ModelScope；国内网络可在 `from_pretrained()` 中传入 `source="modelscope"`。镜像版本滞后及环境混用的处理见[安装指南](https://github.com/Zeaulo/bit-jev/blob/main/docs/GGUF_PACKAGE.zh-CN.md)。
+版本应为 `0.13.10`，导入路径应指向当前环境的 `site-packages/bit_jev`。第二条命令会在本机打开与在线测试同源的 Choice、Noul、Score 页面；首次提交才下载约 1.19 GB 模型。需要从 ModelScope 直接下载时可加 `--source modelscope`，使用 Vulkan 可加 `--device gpu`，旧式单题 JSON 可加 `--once`。下方仍保留完整 Python API 示例。镜像版本滞后及环境混用的处理见[安装指南](https://github.com/Zeaulo/bit-jev/blob/main/docs/GGUF_PACKAGE.zh-CN.md)。
 
 ![bit-jev 训练、蒸馏、量化与 CPU/Vulkan 推理流程](project-flow.zh-CN.png)
 
@@ -74,7 +75,7 @@ I2_S GGUF + float32 指针头
 
 ## 推理示例
 
-推荐使用 pip 包。Windows x64 且 CPU 支持 AVX2 时，bit-jev 0.12.10 wheel 已携带 CPU 与 Vulkan GPU 原生 runner；首次加载会按需下载约 1.19 GB 的模型。使用 `device="cpu"` 或 `device="gpu"` 推理无需 Git、CMake、C++ 编译器或 Vulkan SDK；Vulkan GPU 需要显卡驱动提供 `vulkan-1.dll`。其他系统和 CUDA 后端按需从固定源码构建，需要 Git、CMake 3.28+ 与 C++17 编译器；CUDA 构建还需要 CUDA Toolkit。
+推荐使用 pip 包。Windows x64 且 CPU 支持 AVX2 时，bit-jev 0.13.10 wheel 已携带 CPU 与 Vulkan GPU 原生 runner；首次加载会按需下载约 1.19 GB 的模型。使用 `device="cpu"` 或 `device="gpu"` 推理无需 Git、CMake、C++ 编译器或 Vulkan SDK；Vulkan GPU 需要显卡驱动提供 `vulkan-1.dll`。其他系统和 CUDA 后端按需从固定源码构建，需要 Git、CMake 3.28+ 与 C++17 编译器；CUDA 构建还需要 CUDA Toolkit。
 
 ```python
 from bit_jev.gguf import BitJev