njucckevin / SeeClick

The model, data and code for the visual GUI Agent SeeClick
Apache License 2.0
139 stars 8 forks source link

Pretraining and finetuning code #8

Closed DanielProkhorov closed 4 months ago

DanielProkhorov commented 4 months ago

Would you please provided the pretraining and finetuning code?

Also, why did you pretrained this model and not just finetuned the qwen vl model?

njucckevin commented 4 months ago

We plan to release the data and code for the downstream tasks, as well as the code for finetune, maybe in one week.

njucckevin commented 4 months ago

The fine-tuning code on downstream tasks has been released.