Commit
·
f891dd2
1
Parent(s):
3455ea2
Update README.md
Browse files
README.md
CHANGED
|
@@ -52,7 +52,9 @@ with the original Zephyr dDPO model and other 7B models.
|
|
| 52 |
|
| 53 |
### Chat benchmarks
|
| 54 |
Table adapted from Zephyr-7b-β and Starling's original tables for [MT-Bench](https://huggingface.co/spaces/lmsys/mt-bench) and [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/) benchmarks. Results are shown sorted by AlpacaEval win rates and ommit some >7B for brevity.
|
|
|
|
| 55 |
Notus stays on par with Zephyr on MT-Bench, while surpassing Zephyr, Claude 2, and Cohere Command on AlpacaEval. Making Notus the most-competitive 7B commercial model on AlpacaEval.
|
|
|
|
| 56 |
<table>
|
| 57 |
<tr>
|
| 58 |
<th>Model</th>
|
|
|
|
| 52 |
|
| 53 |
### Chat benchmarks
|
| 54 |
Table adapted from Zephyr-7b-β and Starling's original tables for [MT-Bench](https://huggingface.co/spaces/lmsys/mt-bench) and [AlpacaEval](https://tatsu-lab.github.io/alpaca_eval/) benchmarks. Results are shown sorted by AlpacaEval win rates and ommit some >7B for brevity.
|
| 55 |
+
|
| 56 |
Notus stays on par with Zephyr on MT-Bench, while surpassing Zephyr, Claude 2, and Cohere Command on AlpacaEval. Making Notus the most-competitive 7B commercial model on AlpacaEval.
|
| 57 |
+
|
| 58 |
<table>
|
| 59 |
<tr>
|
| 60 |
<th>Model</th>
|