Commit
•
1cb4251
1
Parent(s):
f8e1f70
change to bar chart
Browse files
README.md
CHANGED
|
@@ -53,7 +53,9 @@ print((tokenizer.decode(outputs[0])))
|
|
| 53 |
|
| 54 |
Zamba2-1.2B-Instruct achieves leading instruction-following and multi-turn chat performance for a model of its size and matches strong models significantly larger. For instance, Zamba2-1.2B-Instruct outperforms Gemma2-2B-Instruct, a very strong model over 2x its size.
|
| 55 |
|
| 56 |
-
<
|
|
|
|
|
|
|
| 57 |
|
| 58 |
| Model | Size | MT-Bench | IFEval |
|
| 59 |
|-------------|----|----|----|
|
|
|
|
| 53 |
|
| 54 |
Zamba2-1.2B-Instruct achieves leading instruction-following and multi-turn chat performance for a model of its size and matches strong models significantly larger. For instance, Zamba2-1.2B-Instruct outperforms Gemma2-2B-Instruct, a very strong model over 2x its size.
|
| 55 |
|
| 56 |
+
<center>
|
| 57 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/65bc13717c6ad1994b6619e9/UdlseqQFDxYvEdLV5xurw.png" width="900"/>
|
| 58 |
+
</center>
|
| 59 |
|
| 60 |
| Model | Size | MT-Bench | IFEval |
|
| 61 |
|-------------|----|----|----|
|