BorisMolch
BorisMolch
@tkirshboim were you able to resolve these 'glob' errors?
From what i manually tested its not better than gptV... i guess we have to wait for vision to improve and provide accurate coordinates https://github.com/OthersideAI/self-operating-computer/issues/7 or take a different approach.
> @BorisMolch even though Llava may not perform well, others may be interested to try it and see how they can improve it. If you want to make a PR...
`LLM did not respond with JSON` here too. openrouter MODEL_NAME=codellama/codellama-70b-instruct
same here ERROR: The prompt size exceeds the context window size and cannot be processed.
same here. trying to read a folder with lots of files. would be great to have some paging for the requests
Goal 1: Search_files and make a descriptions of all files. Goal 2: be aware that you cannot send long requests to the api. i think max is 8k tokens. Goal...
> pip install -U git+https://[email protected]/facebookresearch/encodec#egg=encodec i've tried both. still getting the saem error.
Same here, on windows. i tried using then only 1 screen with same result. I believe the Vision it not providing the coordninates well probably... From my manual tests with...
That would be indeed nice to have build in.