Commit
•
93eb6eb
1
Parent(s):
a4f14de
Update README.md
Browse files
README.md
CHANGED
@@ -7,7 +7,7 @@ datasets:
|
|
7 |
- m-a-p/CodeFeedback-Filtered-Instruction
|
8 |
---
|
9 |
|
10 |
-
# Llama-3-
|
11 |
|
12 |
### Built with Meta Llama 3
|
13 |
|
@@ -17,7 +17,11 @@ datasets:
|
|
17 |
This model was built using a new Smaug recipe for improving performance on real world multi-turn conversations applied to
|
18 |
[meta-llama/Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct).
|
19 |
|
20 |
-
The model outperforms Llama-3-70B-Instruct substantially, and is on par with GPT-4-Turbo, on MT-Bench (see below).
|
|
|
|
|
|
|
|
|
21 |
|
22 |
### Model Description
|
23 |
|
|
|
7 |
- m-a-p/CodeFeedback-Filtered-Instruction
|
8 |
---
|
9 |
|
10 |
+
# Smaug-Llama-3-70B-Instruct
|
11 |
|
12 |
### Built with Meta Llama 3
|
13 |
|
|
|
17 |
This model was built using a new Smaug recipe for improving performance on real world multi-turn conversations applied to
|
18 |
[meta-llama/Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct).
|
19 |
|
20 |
+
The model outperforms Llama-3-70B-Instruct substantially, and is on par with GPT-4-Turbo, on MT-Bench (see below).
|
21 |
+
|
22 |
+
EDIT: Smaug-Llama-3-70B-Instruct is the top open source model on Arena-Hard currently! It is also nearly on par with Claude Opus - see below.
|
23 |
+
|
24 |
+
We are conducting additional benchmark evaluations and will add those when available.
|
25 |
|
26 |
### Model Description
|
27 |
|