chore: configure documentation deployment and update mkdocs settings

- Add GitHub Actions workflow for automated docs deployment
- Add docs/requirements.txt for documentation dependencies
- Remove mkdocs-jupyter plugin from mkdocs.yml
- Update sft_rm.md documentation
- Remove docs/examples symlink
- Add .env to .gitignore

Author: XiaoBoAI

.github/workflows/deploy-docs.yml

@@ -0,0 +1,62 @@
+name: Deploy MkDocs to GitHub Pages
+
+on:
+  push:
+    branches:
+      - main
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  pages: write
+  id-token: write
+
+concurrency:
+  group: pages
+  cancel-in-progress: false
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+
+      - name: Cache pip dependencies
+        uses: actions/cache@v4
+        with:
+          path: ~/.cache/pip
+          key: ${{ runner.os }}-pip-${{ hashFiles('docs/requirements.txt') }}
+          restore-keys: |
+            ${{ runner.os }}-pip-
+
+      - name: Install dependencies
+        run: |
+          pip install --upgrade pip
+          pip install -r docs/requirements.txt
+
+      - name: Build documentation
+        run: mkdocs build --clean
+
+      - name: Upload artifact
+        uses: actions/upload-pages-artifact@v3
+        with:
+          path: ./site
+
+  deploy:
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    runs-on: ubuntu-latest
+    needs: build
+    steps:
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4

.gitignore

@@ -16,4 +16,4 @@ docs/log
 .python-version
 tests/plt_*
 /site
-poetry.lock
+poetry.lock.env

docs/examples

@@ -0,0 +1,5 @@
+mkdocs>=1.5.0
+mkdocs-material>=9.0.0
+mkdocstrings[python]>=0.24.0
+pymdown-extensions>=10.0
+mkdocs-shadcn>=0.1.0

docs/requirements.txt

@@ -2,7 +2,6 @@
 
 This directory contains training scripts for fine-tuning a Reasoning Reward Model based on the VERL framework. The model is designed to evaluate and score responses based on their reasoning quality, supporting both single-node and multi-node distributed training.
 
-[sft_rm.sh](../../../examples/train/sft/sft_rm.sh)
 
 ## Training Approaches Overview
 

docs/tutorial/training_rm/sft_rm.md

@@ -67,7 +67,6 @@ plugins:
       min_search_length: 2
       prebuild_index: true
       indexing: 'full'
-  - mkdocs-jupyter
   - mkdocstrings:
       handlers:
         python: