google-deepmind / google-deepmind/gemma
MMLU script require
Open
enhancement
- Dominant language
- Python
- Stars
- 5.7k
- Forks
- 1k
- Avg merge
- 10h 33m
- Merged PRs (30d)
- 2
Description
I've tried many eval repositry(like lm-eval-harness). None of them can achieve score reported on hf page. So can you offer a script like gsm8k example in this repo ? : )
Contributor guide
Assessment
This issue has not been assessed yet.