Commit
•
ec3bfe8
1
Parent(s):
4e6584e
Update README.md
Browse files
README.md
CHANGED
|
@@ -6,8 +6,6 @@ license: other
|
|
| 6 |
<img src="https://i.ibb.co/DwtwXm8/Arcee-2-magic.png" alt="Arcee Nova" style="border-radius: 10px; box-shadow: 0 4px 8px 0 rgba(0, 0, 0, 0.2), 0 6px 20px 0 rgba(0, 0, 0, 0.19); max-width: 100%; height: auto;">
|
| 7 |
</div>
|
| 8 |
|
| 9 |
-
## Overview
|
| 10 |
-
|
| 11 |
Arcee-Nova is our highest performing open source model. Evaluated on the same stack as the OpenLLM Leaderboard 2.0, making it the top-performing open source model tested on that stack. Its performance approaches that of GPT-4 from May 2023, marking a significant milestone.
|
| 12 |
|
| 13 |
Nova is a merge of Qwen2-72B-Instruct with a custom model tuned on a generalist dataset mixture.
|
|
|
|
| 6 |
<img src="https://i.ibb.co/DwtwXm8/Arcee-2-magic.png" alt="Arcee Nova" style="border-radius: 10px; box-shadow: 0 4px 8px 0 rgba(0, 0, 0, 0.2), 0 6px 20px 0 rgba(0, 0, 0, 0.19); max-width: 100%; height: auto;">
|
| 7 |
</div>
|
| 8 |
|
|
|
|
|
|
|
| 9 |
Arcee-Nova is our highest performing open source model. Evaluated on the same stack as the OpenLLM Leaderboard 2.0, making it the top-performing open source model tested on that stack. Its performance approaches that of GPT-4 from May 2023, marking a significant milestone.
|
| 10 |
|
| 11 |
Nova is a merge of Qwen2-72B-Instruct with a custom model tuned on a generalist dataset mixture.
|