How to Fine-Tune

[shiwenwen]

I want to use the page data of our own APP for further fine-tuning training based on OmniParser to improve the accuracy of recognition, but I don't know how to fine-tune, do you have any instructions?

[Abstracting]

I had the same question. Information on This would appreciated

[yadong-lu]

Hi @shiwenwen, the data releasing is more restricted than the model release in our internal policy. However, we are exploring options for it releasing data in the future.

[abrichr]

Hi @yadong-lu , would it be possible to release the fine-tuning code independently of the data?

[matbee-eth]

Hi @shiwenwen, the data releasing is more restricted than the model release in our internal policy. However, we are exploring options for it releasing data in the future.

How about dataset formatting? Then we could just continued-training the model with custom data instead of training from scratch (if feasible)