[FEATURE] Is it possible for adding hparams to model.default_cfg?

[luckyhug]

Is your feature request related to a problem? Please describe. When I search for some model: https://huggingface.co/timm/convnext_large_mlp.clip_laion2b_augreg_ft_in1k_384, the model card said it was fine-tuned on ImageNet-1k in timm by Ross Wightman. Though it is directed to some more details on pretrain, the hparams for this finetuning process are hard to find.

Describe the solution you'd like Maybe we could add the hparams in model.finetune_cfg to provide more useful information?

Describe alternatives you've considered or maybe the args.yaml file can be provided or linked to the model card?

Additional context Thank you very much! I found some convnext hparams on https://gist.github.com/rwightman/ee0b02c1e99a0761264d1d1319e95e5b but only for nano and atto, I'm not sure if they are still a strong hparams for finetuning large models? Should I start my sweep based on these much smaller models hparams?