Document AniFileBERT maintenance workflow

ANDROID.md

@@ -1,10 +1,11 @@
 # Android export and runtime
 
-This folder is a normal MiruPlay subdirectory, not a Git submodule. It contains
-the Python training pipeline plus an ONNX export path for Android.
+This repository is used by MiruPlay as a Git submodule at
+`tools/anime_parser`. It contains the Python training pipeline plus an ONNX
+export path for Android.
 
 For the full scanner integration notes, file-vs-folder behavior, and device
-test procedure, see [`../../docs/anime-filename-parser.md`](../../docs/anime-filename-parser.md).
+test procedure, see MiruPlay's `docs/anime-filename-parser.md`.
 
 ## Export
 
@@ -12,7 +13,7 @@ From `tools/anime_parser`:
 
 ```bash
 python -m pip install -r requirements.txt
-python export_onnx.py --model-dir checkpoints/final --android-assets-dir ../../scraper/src/main/assets/anime_parser
+python export_onnx.py --model-dir checkpoints/dmhy-finetune/final --android-assets-dir ../../scraper/src/main/assets/anime_parser
 ```
 
 The exporter writes:
@@ -30,7 +31,7 @@ The ONNX graph uses fixed Android inputs:
 - `logits`: `float32[1,64,15]`
 
 The current export was verified against PyTorch with max absolute logits
-difference `2.5033950805664062e-05`.
+difference `1.621246337890625e-05`.
 
 ## Runtime
 

MAINTENANCE.md

@@ -0,0 +1,111 @@
+# AniFileBERT Maintenance
+
+This repository is the standalone Hugging Face model repo used by MiruPlay as
+`tools/anime_parser`.
+
+## Related Repositories
+
+| Repository | URL | Purpose |
+|------------|-----|---------|
+| AniFileBERT | `https://huggingface.co/ModerRAS/AniFileBERT` | Model, training scripts, ONNX export |
+| AnimeName | `https://huggingface.co/datasets/ModerRAS/AnimeName` | Training datasets and manifests |
+| MiruPlay | `https://github.com/ModerRAS/MiruPlay` | Android app and runtime integration |
+
+Nested structure:
+
+```text
+AniFileBERT
+  datasets/AnimeName -> ModerRAS/AnimeName
+```
+
+## Clone
+
+```bash
+git clone --recursive https://huggingface.co/ModerRAS/AniFileBERT
+```
+
+After a normal clone:
+
+```bash
+git submodule update --init --recursive
+```
+
+## Dataset Waterline
+
+Current DMHY snapshot:
+
+```text
+last_file_id: 689304
+next_min_id: 689305
+labeled_samples: 263042
+mixed_train_samples: 363042
+```
+
+The authoritative dataset files live in `datasets/AnimeName`.
+
+## Train
+
+```bash
+python -m pip install -r requirements.txt
+python train.py \
+  --data-file datasets/AnimeName/mixed_train.jsonl \
+  --vocab-file datasets/AnimeName/vocab.json \
+  --save-dir checkpoints/dmhy-finetune \
+  --init-model-dir . \
+  --epochs 1 \
+  --batch-size 128 \
+  --learning-rate 0.0003 \
+  --warmup-steps 300 \
+  --seed 42
+```
+
+## Publish a New Checkpoint
+
+Copy the final checkpoint to the repository root:
+
+```powershell
+Copy-Item checkpoints/dmhy-finetune/final/config.json . -Force
+Copy-Item checkpoints/dmhy-finetune/final/model.safetensors . -Force
+Copy-Item checkpoints/dmhy-finetune/final/tokenizer_config.json . -Force
+Copy-Item checkpoints/dmhy-finetune/final/training_args.bin . -Force
+Copy-Item checkpoints/dmhy-finetune/final/vocab.json . -Force
+```
+
+Then commit and push:
+
+```bash
+git add .
+git commit -m "Update AniFileBERT checkpoint"
+git push origin main
+```
+
+## Update the Dataset Submodule
+
+After pushing new files to `ModerRAS/AnimeName`, update the nested pointer:
+
+```bash
+git submodule update --remote datasets/AnimeName
+git add datasets/AnimeName
+git commit -m "Update AnimeName dataset pointer"
+git push origin main
+```
+
+## Update MiruPlay
+
+From the MiruPlay root:
+
+```bash
+git submodule update --remote --recursive tools/anime_parser
+git add tools/anime_parser
+git commit -m "Update AniFileBERT submodule"
+git push origin master
+```
+
+If a new ONNX export changed Android runtime assets, also stage:
+
+```text
+scraper/src/main/assets/anime_parser/anime_filename_parser.onnx
+scraper/src/main/assets/anime_parser/config.json
+scraper/src/main/assets/anime_parser/vocab.json
+```
+

README.md

@@ -128,6 +128,16 @@ python export_onnx.py --model-dir checkpoints/dmhy-finetune/final --output expor
 - `export_onnx.py`: ONNX export for Android integration
 - `exports/`: exported ONNX model and metadata
 - `data/dmhy/*.manifest.json`: dataset waterlines and counts
+- `datasets/AnimeName/`: nested dataset submodule
+
+## Maintenance Notes
+
+MiruPlay tracks this repository as `tools/anime_parser`, and this repository
+tracks `ModerRAS/AnimeName` as `datasets/AnimeName`. After updating either
+repo, remember to commit the submodule pointer in the parent repo.
+
+For the full maintenance workflow, see MiruPlay's
+`docs/anifilebert-maintenance.md`.