Closed oximi123 closed 8 months ago
Is there a way to evaluate the benchmark with local model like LLama or Vicuna using FastChat ?
@oximi123 Refer to evaluator.py and utils.py to implement a Wrapper, and modify the content of evaluator.py for testing.
evaluator.py
utils.py
Is there a way to evaluate the benchmark with local model like LLama or Vicuna using FastChat ?