Request for model.config_file for evaluating official pre-trained DINOv3 models

[Rxx01]

I would like to evaluate the official pre-trained models on downstream tasks such as:

Logistic regression classification on ImageNet-1k

k-NN classification on ImageNet-1k

Linear classification with data augmentation on ImageNet-1k

The training code requires a model.config_file to run evaluation. However, I could not find a provided config.yaml for the official pre-trained models.

Could you please provide a model.config_file suitable for evaluating the official pre-trained DINOv3 models?

For reference, the evaluation commands are as follows:

Logistic regression

PYTHONPATH=${PWD} python -m dinov3.run.submit dinov3/eval/log_regression.py
model.config_file=<PATH/TO/OUTPUT/DIR>/config.yaml
model.pretrained_weights=<PATH/TO/OUTPUT/DIR>/teacher_checkpoint.pth
output_dir=<PATH/TO/OUTPUT/DIR>
train.dataset=ImageNet:split=TRAIN:root=<PATH/TO/DATASET>:extra=<PATH/TO/DATASET>
eval.test_dataset=ImageNet:split=VAL:root=<PATH/TO/DATASET>:extra=<PATH/TO/DATASET>

k-NN

PYTHONPATH=${PWD} python -m dinov3.run.submit dinov3/eval/knn.py
model.config_file=<PATH/TO/OUTPUT/DIR>/config.yaml
model.pretrained_weights=<PATH/TO/OUTPUT/DIR>/teacher_checkpoint.pth
output_dir=<PATH/TO/OUTPUT/DIR>
train.dataset=ImageNet:split=TRAIN:root=<PATH/TO/DATASET>:extra=<PATH/TO/DATASET>
eval.test_dataset=ImageNet:split=VAL:root=<PATH/TO/DATASET>:extra=<PATH/TO/DATASET>

Linear classification with data augmentation

PYTHONPATH=${PWD} python -m dinov3.run.submit dinov3/eval/linear.py
model.config_file=<PATH/TO/OUTPUT/DIR>/config.yaml
model.pretrained_weights=<PATH/TO/OUTPUT/DIR>/teacher_checkpoint.pth
output_dir=<PATH/TO/OUTPUT/DIR>
train.dataset=ImageNet:split=TRAIN:root=<PATH/TO/DATASET>:extra=<PATH/TO/DATASET>
train.val_dataset=ImageNet:split=VAL:root=<PATH/TO/DATASET>:extra=<PATH/TO/DATASET>

[randomze]

I'm also wondering how to do this. Is it possible to use the dino_hub argument with the local weights?