Instructions to use HuggingSelf/test0519 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Bagel
How to use HuggingSelf/test0519 with Bagel:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Unified-Bench old protocol reproduction bundle
This folder contains the assets used to reproduce the historical raw BAGEL
Unified-Bench score 0.8345940754981711 under the old TorchUMM protocol.
HF path prefix:
HuggingSelf/test0519/unified_bench_old_protocol_0p8346
Contents
inputs/unified_bench/Image/: the 100 Unified-Bench reference input images.outputs/raw_bagel/images/: raw BAGEL round-trip generated images.outputs/raw_bagel/captions.jsonl: image-to-text captions produced by raw BAGEL.outputs/raw_bagel/summary.json: original old-protocol score JSON.scorers/dinov3-vitl16_old_protocol/: the old DINOv3 scorer checkpoint used by the historical run.configs/unified_bench_bagel.yaml: old TorchUMM Unified-Bench config.scripts/reproduce_apr4_unified_bagel_score.py: Modal-side reproduction helper used to verify the score.scripts/run_scoring.pyandscripts/scorers/: scoring code snapshot from TorchUMM.manifest.json: hashes, counts, paths, and expected scores.
Expected Score
| scorer | average |
|---|---|
| CLIP | 0.894650644659996 |
| DINOv2 | 0.787667881194502 |
| DINOv3 old protocol | 0.723970373794436 |
| LongCLIP | 0.932087402343750 |
| Overall | 0.834594075498171 |
Overall is the mean of the four scorer averages.
DINOv3
Old-protocol DINOv3 file:
scorers/dinov3-vitl16_old_protocol/model.safetensors
Expected SHA256:
dcb2e45127cccbf1601e5f42fef165eea275c8e5213197e8dcf3f48822718179
The newer cached DINOv3 weight we tested separately produced very high reference-to-reference similarity and should not be mixed with this old protocol score.
Reproduction Notes
The historical run was verified on Modal workspace aifrontierwm using:
ref_dir = /datasets/unified_bench/Image
gen_dir = /output-apr4/unified_bench/bagel/images
Scoring model paths:
clip = /model_cache/unified_bench/clip-vit-large-patch14
dinov2 = /model_cache/unified_bench/dinov2-large
dinov3 = /model_cache/unified_bench/dinov3-vitl16
longclip = /model_cache/unified_bench/longclip-L.pt
The bundle includes the old DINOv3 directory because this is the piece that made
the old protocol reproducible. CLIP, DINOv2, and LongCLIP are public/downloadable
from the sources listed in manifest.json.
Minimal Download Example
from huggingface_hub import snapshot_download
root = snapshot_download(
repo_id="HuggingSelf/test0519",
repo_type="model",
allow_patterns=["unified_bench_old_protocol_0p8346/**"],
)
print(root)
After downloading, point TorchUMM's Unified-Bench scorer at:
ref_dir: <download_root>/unified_bench_old_protocol_0p8346/inputs/unified_bench/Image
out_dir: <download_root>/unified_bench_old_protocol_0p8346/outputs/raw_bagel
dinov3: <download_root>/unified_bench_old_protocol_0p8346/scorers/dinov3-vitl16_old_protocol