Junlei Zhang

What pre-trained models do you use to retrieve negative embeddings?

1

Hello, thank you for releasing your code. When I want to reproduce your results, I only get 78.6 for RoBERTa_large. I noticed that you do not mention what pre-trained models...

Hello, Thank you for your work. Could you please give some advice about how to run BERT with Monarch?

Could you please provide the complete offline evaluation code for mm-mind2web? Currently, only the prediction demo code is available, lacking the full dataset loop and evaluation metric to reproduce the...

Thank you very much for your work. I have found a potential bug in your MM-Mind2web model. It seems that each data point only contains a list of selectable actions...

Dear, Thank you for your excellent job. Would you release the 300k sft data?

Errors in annotation

9

I found some errors in annotion. In the classifieds_10: sites: ['classifieds'] task_id: 10 require_login: True storage_state: ./.auth/classifieds_state.json start_url: http://localhost:9980 geolocation: None intent_template: What is the {{attribute}} of {{item}}? intent: What...

How to navigate to www.homepage.com?

3

Thank you for your work. I can come to the the homepage with http://127.0.0.1:4399 but not the www.homepage.com. Do I have to change the host of my server ot navigate...

How to only save adapter_model when training with Lora. [Feature]

2

### Motivation  Thank you for your work. I trained Internvl 70b with Lora on LLM. But I found every times it saved all parameters instead of the adapter_model. How...

The very important element: "sort" can not be found in accessibility_tree_with_captioner.

2

Hello, when I try to run the models with accessibility_tree_with_captioner. I found that sort can not be found in the accessibility_tree_with_captioner. There is only a staticText of sort but no...