Results 10 comments of Blake

Try replacing `page.type("input[name='username']", "test")` with `page.evaluate("document.querySelector(\"input[name='username'\").value = 'test';")`

> @orrzohar yes, the model supports batching. For that you just have to pass the prompts as a list of strings, and also the list of visuals. Also you can...

think it'd be straight forward to swap the vicuna-7b for a llama-3-8b base? e.g. https://huggingface.co/lmms-lab/llama3-llava-next-8b

+1 would love to try out a qlora/lora fine tune

can't simply using huggingface+transformers b/c it's missing a preprocessor_config.json