DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-MADNESS

MN GRAND Gutenberg Lyra4 12B Madness

Release Date

Oct 11th, 2024

Parameters

12B

Context Size

16k

Creative writing

8.97%

Rule following

12.02%

Utility

48.67%

Mathematics

50.00%

Tooling

50.77%

Language

65.96%

Logic

50.00%

Dialogue tags

Various tasks related to dialogue tags in text.

Scenario Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Total
0-shot Creative writingRule following
14%14%1%1%1%1%0%0%0%0%3%
0-shot Creative writingRule following
50%50%38%1%0%0%0%0%0%0%14%
0-shot Creative writingRule following
66%50%50%29%27%15%4%4%0%0%25%
0-shot Creative writingRule following
42%10%0%0%0%0%0%0%0%0%5%
0-shot Creative writingRule following
50%49%0%0%0%0%0%0%0%0%10%
0-shot Creative writingRule following
12%0%0%0%0%0%0%0%0%0%1%
0-shot Creative writingRule following
48%1%0%0%0%0%0%0%0%0%5%
8.97%

Language Comprehension

Does the model understand more than just English?

Scenario Run 1 Run 2 Run 3 Run 4 Run 5 Total
0-shot Language
100%100%100%100%100%100%
0-shot Language
100%100%100%100%100%100%
0-shot Language
100%100%100%100%0%80%
0-shot Language
100%100%100%100%100%100%
95.00%

Language Writing

Can the model generate text in different languages?

Scenario Run 1 Run 2 Run 3 Run 4 Run 5 Total
0-shot Language
100%79%64%0%0%48%
0-shot Language
50%50%43%0%0%29%
0-shot Language
90%70%67%50%0%55%
0-shot Language
100%40%0%0%0%28%
0-shot Language
100%67%50%50%0%53%
42.74%

Tool usage within Novelcrafter

Output messages that are related to tool usage within Novelcrafter

Scenario Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Total
0-shot ToolingUtility
33%33%33%0%0%0%0%0%0%0%10%
10.00%

N-Length Sentences

Write sentences with exactly N words

Scenario Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Total
0-shot Rule following
52%32%21%15%9%8%8%5%4%3%16%
0-shot Rule following
31%26%20%20%19%18%13%13%12%7%18%
0-shot Rule following
17%16%11%10%10%7%6%6%2%0%9%
14.04%

Voice/dialogue sheets

Extract dialogue from given text as voice sheets.

Scenario Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Total
0-shot Utility
100%100%0%0%0%0%0%0%0%0%20%
1-shot Utility
100%100%0%0%0%0%0%0%0%0%20%
Few-shot Utility
100%100%100%100%100%0%0%0%0%0%50%
0-shot Utility
0%0%0%0%0%0%0%0%0%0%0%
0-shot Utility
100%0%0%0%0%0%0%0%0%0%10%
20.00%

Write N of X

Write exactly N words/sentences/paragraphs...

Scenario Run 1 Run 2 Run 3 Run 4 Run 5 Run 6 Run 7 Run 8 Run 9 Run 10 Total
0-shot Rule following
0%0%0%0%0%0%0%0%0%0%0%
0-shot Rule following
2%0%0%0%0%0%0%0%0%0%0%
0-shot Rule following
0%0%0%0%0%0%0%0%0%0%0%
0-shot Rule following
0%0%0%0%0%0%0%0%0%0%0%
0-shot Rule following
0%0%0%0%0%0%0%0%0%0%0%
0-shot Rule following
100%100%98%77%77%9%2%0%0%0%46%
0-shot Rule following
100%54%2%0%0%0%0%0%0%0%16%
0-shot Rule following
100%100%100%100%77%54%54%0%0%0%58%
0-shot Rule following
9%2%0%0%0%0%0%0%0%0%1%
0-shot Rule following
0%0%0%0%0%0%0%0%0%0%0%
0-shot Rule following
100%100%100%0%0%0%0%0%0%0%30%
0-shot Rule following
100%0%0%0%0%0%0%0%0%0%10%
0-shot Rule following
100%0%0%0%0%0%0%0%0%0%10%
13.20%