nvidia/llama-3.1-nemotron-70b-instruct

Llama 3.1 Nemotron 70B

Release Date

Oct 15th, 2024

Parameters

70B

Context Size

128k

Creative writing

27.60%

Rule following

67.08%

Utility

77.67%

Mathematics

100.00%

Tooling

88.46%

Language

44.28%

Logic

78.75%

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%61%96%
0-shot Creative writingRule following
50%47%34%18%5%0%0%0%0%0%15%
0-shot Creative writingRule following
50%39%36%17%15%1%0%0%0%0%16%
0-shot Creative writingRule following
97%52%52%51%51%50%50%26%19%0%45%
0-shot Creative writingRule following
38%0%0%0%0%0%0%0%0%0%4%
0-shot Creative writingRule following
11%1%0%0%0%0%0%0%0%0%1%
0-shot Creative writingRule following
49%43%38%23%5%2%2%1%1%0%16%
27.60%

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%0%80%
0-shot Language
100%100%100%100%0%80%
0-shot Language
100%100%100%0%0%60%
0-shot Language
100%0%0%0%0%20%
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
50%0%0%0%0%10%
0-shot Language
44%0%0%0%0%9%
0-shot Language
100%86%67%0%0%50%
0-shot Language
100%100%86%50%0%67%
0-shot Language
60%50%0%0%0%22%
31.70%

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%100%100%100%100%100%100%100%
100.00%

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
100%100%100%100%100%100%100%100%100%100%100%
0-shot Rule following
100%100%100%100%100%97%97%97%95%95%98%
0-shot Rule following
66%55%52%45%43%37%30%29%27%27%41%
79.78%

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
0%0%0%0%0%0%0%0%0%0%0%
1-shot Utility
100%100%100%100%100%100%0%0%0%0%60%
Few-shot Utility
100%100%100%100%100%100%100%100%100%0%90%
0-shot Utility
0%0%0%0%0%0%0%0%0%0%0%
0-shot Utility
0%0%0%0%0%0%0%0%0%0%0%
30.00%