Commit
•
b79cb15
1
Parent(s):
751ddef
Update README.md
Browse files
README.md
CHANGED
|
@@ -61,9 +61,10 @@ We find that Zamba performs significantly better than existing open models (with
|
|
| 61 |
|
| 62 |
|
| 63 |
<center>
|
| 64 |
-
<img src="https://cdn-uploads.huggingface.co/production/uploads/65c05e75c084467acab2f84a/
|
| 65 |
</center>
|
| 66 |
|
|
|
|
| 67 |
Due to its SSM architecture, Zamba is extremely efficient in inference, substantially outperforming comparable 7B and 8B models in inference latency as well as memory cost of generation due to its substantially diminished KV cache.
|
| 68 |
|
| 69 |
<center>
|
|
|
|
| 61 |
|
| 62 |
|
| 63 |
<center>
|
| 64 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/65c05e75c084467acab2f84a/FG73iXpiDGSX_opbDJxKo.png" width="400" alt="Zamba performance">
|
| 65 |
</center>
|
| 66 |
|
| 67 |
+
|
| 68 |
Due to its SSM architecture, Zamba is extremely efficient in inference, substantially outperforming comparable 7B and 8B models in inference latency as well as memory cost of generation due to its substantially diminished KV cache.
|
| 69 |
|
| 70 |
<center>
|