ai21/jamba-1-5-large

AI21 Jamba 1.5 Large

Release Date

Aug 22nd, 2024

Parameters

398B MoE

Context Size

256k

Creative writing

36.93%

Rule following

52.09%

Utility

44.11%

Mathematics

50.00%

Tooling

35.64%

Language

68.38%

Logic

43.75%

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
100%100%100%100%100%100%100%100%100%100%100%
0-shot Creative writingRule following
49%49%43%10%7%5%3%1%0%0%17%
0-shot Creative writingRule following
99%94%57%51%50%48%16%15%7%0%44%
0-shot Creative writingRule following
99%99%97%68%59%47%34%18%14%0%54%
0-shot Creative writingRule following
50%45%41%27%23%2%1%0%0%0%19%
0-shot Creative writingRule following
52%48%32%3%0%0%0%0%0%0%14%
0-shot Creative writingRule following
50%49%22%0%0%0%0%0%0%0%12%
36.93%

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%0%80%
0-shot Language
100%100%100%0%0%60%
0-shot Language
0%0%0%0%0%0%
60.00%

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
95%93%86%60%50%77%
0-shot Language
100%100%85%81%50%83%
0-shot Language
100%91%88%77%72%85%
0-shot Language
100%100%100%50%0%70%
0-shot Language
100%100%50%50%0%60%
75.09%

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
100%100%100%100%67%67%0%0%0%0%53%
53.33%

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
100%96%89%82%79%78%78%78%40%2%72%
0-shot Rule following
100%100%87%85%83%74%74%74%30%25%73%
0-shot Rule following
0%0%0%0%0%0%0%0%0%0%0%
48.46%

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%100%100%100%0%0%0%0%0%50%
1-shot Utility
100%100%100%100%100%0%0%0%0%0%50%
Few-shot Utility
100%100%100%100%100%100%100%100%0%0%80%
0-shot Utility
0%0%0%0%0%0%0%0%0%0%0%
0-shot Utility
100%100%100%100%0%0%0%0%0%0%40%
44.00%

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
100%100%100%100%92%92%92%0%0%0%68%
0-shot Rule following
100%100%100%98%92%77%77%54%9%0%71%
0-shot Rule following
100%100%100%100%100%98%92%77%0%0%77%
0-shot Rule following
92%92%77%77%54%27%9%2%0%0%43%
0-shot Rule following
0%0%0%0%0%0%0%0%0%0%0%
0-shot Rule following
100%100%100%100%100%100%100%100%100%100%100%
0-shot Rule following
100%100%100%100%100%100%100%100%100%100%100%
0-shot Rule following
100%100%100%100%100%98%92%92%92%77%95%
0-shot Rule following
100%92%77%27%9%0%0%0%0%0%31%
0-shot Rule following
0%0%0%0%0%0%0%0%0%0%0%
0-shot Rule following
100%100%100%100%100%100%100%100%100%100%100%
0-shot Rule following
100%100%100%100%100%100%100%100%100%0%90%
0-shot Rule following
100%100%0%0%0%0%0%0%0%0%20%
61.09%