This repository contains a mixed precision version of lodestones/taggerine.
The backbone weights are converted to bf16 and the projection head weights are kept in fp32.

Why? – Because the original ReadMe states that the backbone was trained in bf16, so I'm thinking keeping it in fp32 is waste of storage space and bandwidth depending on situation.
There are full bf16 and full fp8 versions here for those interested.

Original ReadMe content

DINOv3 ViT-H/16+ Booru Tagger

A multi-label image tagger trained on e621 and Danbooru annotations, using a DINOv3 ViT-H/16+ backbone fine-tuned end-to-end with a single linear projection head.

Model Details

Property	Value
Backbone	`facebook/dinov3-vith16plus-pretrain-lvd1689m`
Architecture	ViT-H/16+ · 32 layers · hidden dim 1280 · 20 heads · SwiGLU MLP · RoPE · 4 register tokens
Head	`Linear((1 + 4) × 1280 → 74 625)` — CLS + 4 register tokens concatenated
Vocabulary	74 625 tags (min frequency ≥ 50 across training set)
Input resolution	Any multiple of 16 px — trained at 512 px, generalises to higher resolutions
Input normalisation	ImageNet mean/std `[0.485, 0.456, 0.406]` / `[0.229, 0.224, 0.225]`
Output	Raw logits — apply `sigmoid` for per-tag probabilities
Parameters	~632 M (backbone) + ~480 M (head)

Training

Hyperparameter	Value
Training data	e621 + Danbooru (parquet)
Batch size	32
Learning rate	1e-6
Warmup steps	50
Loss	`BCEWithLogitsLoss` with per-tag `pos_weight = (neg/pos)^(1/T)`, cap 100
Optimiser	AdamW (β₁=0.9, β₂=0.999, wd=0.01)
Precision	bfloat16 (backbone) / float32 (projection + loss)
Hardware	2× GPU, ThreadPoolExecutor + NCCL all-reduce

Usage

1. Install dependencies

pip install -r requirements.txt

Or manually:

bash

pip install torch torchvision safetensors Pillow requests \
            python-multipart fastapi uvicorn jinja2 aiofiles

2. Download model files

bash

huggingface-cli download lodestones/taggerine \
    tagger_proto.safetensors \
    tagger_vocab_with_categories_and_alias_updated.json \
    tagger_ui_server.py \
    inference_tagger_standalone.py \
    --local-dir .

Note: tagger_proto.safetensors is ~5.3 GB. Make sure you have enough disk space.

3. Download the `tagger_ui/` templates folder

The server requires the tagger_ui/templates/ directory to be present alongside tagger_ui_server.py:

bash

huggingface-cli download lodestones/taggerine \
    --include "tagger_ui/**" \
    --local-dir .

4. Run the Web UI

bash

python tagger_ui_server.py \
    --checkpoint tagger_proto.safetensors \
    --vocab tagger_vocab_with_categories_and_alias_updated.json \
    --port 7860
# → open http://localhost:7860

CPU-only machine? Add --device cpu (inference will be slower):

bash

python tagger_ui_server.py \
    --checkpoint tagger_proto.safetensors \
    --vocab tagger_vocab_with_categories_and_alias_updated.json \
    --device cpu \
    --port 7860

Standalone CLI inference (no server)

bash

python inference_tagger_standalone.py \
    --checkpoint tagger_proto.safetensors \
    --vocab tagger_vocab_with_categories_and_alias_updated.json \
    --images photo.jpg \
    --topk 30

Files

File	Description
`tagger_proto.safetensors`	Model weights (bfloat16)
`tagger_vocab_with_categories_and_alias_updated.json`	`{"idx2tag": [...], "tag2category": {...}}` — 74 625 tags with category metadata
`tagger_vocab_with_categories.json`	Same without alias data
`tagger_vocab.json`	Minimal vocab — `{"idx2tag": [...]}` only
`inference_tagger_standalone.py`	Self-contained CLI inference script (no `transformers` dep)
`tagger_ui_server.py`	FastAPI + Jinja2 web UI server
`requirements.txt`	Python dependencies

Tag Vocabulary

Tags are sourced from e621 and Danbooru annotations and cover:

Subject — species, character count, gender (solo, duo, anthro, 1girl, male, …)
Body — anatomy, fur/scale/skin markings, body parts
Action / pose — looking at viewer, sitting, …
Scene — background, lighting, setting
Style — digital art, hi res, sketch, watercolor, …
Rating — explicit content tags are included; filter as needed for your use case

Minimum tag frequency threshold: 50 occurrences across the combined dataset.

Limitations

Evaluated on booru-style illustrations and furry art; performance on photographic images or other art works to some extend.
The vocabulary reflects the biases of e621 and Danbooru annotation practices.

License

Apache 2.0

DraconicDragon/taggerine-mixed-bf16

Repository Info:

DINOv3 ViT-H/16+ Booru Tagger

Model Details

Training

Usage

1. Install dependencies

2. Download model files

3. Download the tagger_ui/ templates folder

4. Run the Web UI

Standalone CLI inference (no server)

Files

Tag Vocabulary

Limitations

License

DraconicDragon/
taggerine-mixed-bf16

3. Download the `tagger_ui/` templates folder