Vision_by_Language icon indicating copy to clipboard operation
Vision_by_Language copied to clipboard

use llama

Open zjjJacinthe opened this issue 1 year ago • 1 comments

I want to replace the gpt-turbo-3.5 model in the code with a llama series model. What do I need to do?

zjjJacinthe avatar Apr 29 '24 02:04 zjjJacinthe

Hey, The gpt-3.5-turbo model call is being made here: https://github.com/ExplainableML/Vision_by_Language/blob/master/src/utils.py#L180. You would need to replace the API call with your call to a LLaMa model, the prompt (with the in-context examples) is already available here.

sgk98 avatar May 04 '24 02:05 sgk98