Next try actually teaching it to see by training a projector with a vision encoder on gpt-oss.
About to release GPT-OSS-120B-Vision and GPT-OSS-20B-Vision, how about that! :D
too slow bro
might be slower, but then it can get the actual image as input, not just some description of it
About to release GPT-OSS-120B-Vision and GPT-OSS-20B-Vision, how about that! :D
too slow bro
might be slower, but then it can get the actual image as input, not just some description of it