DanyWin

Hi @Narsil With @mbrunel [we wrote an article](https://blog.mithrilsecurity.io/p/ff5a9670-4eaf-44c6-99d5-009438a9db64/) to explain the motivation of porting Tokenizers to the client side, plus we added insights about to do it. Could you have...

Hi @liebkne ! As @JoFrost mentioned we do not support that yet. Could you give us more details about the model and the workflow you want to cover with BlindAI...

Ok I see. `token_type_ids` are more relevant to provide information when you train on some classification tasks like question answering. This information is not needed for inference. Regarding `attention_mask`, if...

Hi there! Sorry to see those issues. We will have a look. @mbrunel maybe? It might be related to recent changes

Hmm it might be because the model did not understand the request. Can you try using GPT-3.5 or GPT4?

Pretty cool @shubhamofbce! I think we can assume people will mostly be using LaVague through a CLI, the notebooks were more a low cost solution we chose to make it...

Also, tried using that for the GUI, seems to be working: ```python from playwright.async_api import async_playwright playwright = await async_playwright().start() browser = await playwright.chromium.launch(headless = False) page = await browser.new_page()...

It works! Pretty cool, thanks for a great job! I have a few things to highlight that might be relevant before we merge, some you can help with, some we...

@shubhamofbce super! Will have a look Also regarding the second point I don't think it's actually possible and your solution might be the only one working with Playwright

@shubhamofbce I agree let's see later. In any way, we got big stuff coming that will solve it: - VS Code extension that provides more flexibility that will replace Gradio...