MayaPH
/

GodziLLa2-70B

Text Generation

text-generation-inference

Model card Files Files and versions

jaspercatapang commited on Jan 12

Commit

78102fc

•

1 Parent(s): a7e4cce

Update README.md

Files changed (1) hide show

README.md +4 -1

README.md CHANGED Viewed

@@ -27,7 +27,10 @@ GodziLLa 2 70B is an experimental combination of various proprietary LoRAs from
 | Winogrande (5-shot)   | 83.19  |
 | GSM8K (5-shot)        | 43.21  |
 | DROP (3-shot)         | 52.31  |
-| Average               | 67.01  |
 According to the leaderboard description, here are the benchmarks used for the evaluation:
 - [MMLU](https://arxiv.org/abs/2009.03300) (5-shot) - a test to measure a text model’s multitask accuracy. The test covers 57 tasks including elementary mathematics, US history, computer science, law, and more.

 | Winogrande (5-shot)   | 83.19  |
 | GSM8K (5-shot)        | 43.21  |
 | DROP (3-shot)         | 52.31  |
+| Average (w/ DROP)     | 67.01  |
+| Average (w/o DROP)    | 69.46  |
+Note: As of December 1, 2023, [DROP](https://arxiv.org/abs/1903.00161) is removed from the leaderboard benchmarks.
 According to the leaderboard description, here are the benchmarks used for the evaluation:
 - [MMLU](https://arxiv.org/abs/2009.03300) (5-shot) - a test to measure a text model’s multitask accuracy. The test covers 57 tasks including elementary mathematics, US history, computer science, law, and more.