`eval.py` uses older version of lm_eval

pytorch-labs / gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

BSD 3-Clause "New" or "Revised" License

5.57k stars 507 forks source link

`eval.py` uses older version of lm_eval #89

Closed nairbv closed 7 months ago

nairbv commented 8 months ago

eval.py uses lm_eval.base.BaseLM which doesn't seem to exist in the latest version of lm_eval. (appears to be from lm_eval version 0.3.0, and seems to have been removed in 0.4.0).

the eval.py could be updated to use the latest version or might want to set an explicit version dependency somewhere.

yanboliang commented 8 months ago

This has been fixed by https://github.com/pytorch-labs/gpt-fast/pull/91