docs: 重构 README 结构，全文档添加目录导航

- README 新增 Getting Started 端到端流程，整合快速开始与演示，去重精简
- 中文 README 同步英文版结构，预处理配置改用 seq 策略
- inference.md 补充 SSE 流式格式、错误响应、/stats 端点文档
- params.md 扩展为 CLI 参考，覆盖 server/generate/preprocess 参数表
- dataflow.md 拆分 tokenization/format detection/backend 子节，新增流程图
- architecture/training/inference/preprocessing 均添加目录导航
- 移除 README CI badge

assets/docs/training.md

@@ -1,5 +1,18 @@
 # Training
 
+## Contents
+
+- [Autoregression](#autoregression)
+- [Causal Mask](#causal-mask)
+- [Rotary Position Embedding (RoPE)](#rotary-position-embedding-rope)
+- [Training Loop](#training-loop)
+- [Strategies](#strategies) — SEQ, SFT, DPO, GRPO
+- [LR Schedulers](#lr-schedulers)
+- [Gradient Checkpointing](#gradient-checkpointing)
+- [Checkpoint](#checkpoint)
+- [TrainContextBuilder](#traincontextbuilder-builder-pattern)
+- [Training CLI](#training-cli)
+
 ### Autoregression
 
 Given a token sequence, the model predicts the probability of the next token. Each generated token is appended to the input and fed back, repeating until an end-of-sequence token or max length.