Update README.md
Browse files
README.md
CHANGED
|
@@ -61,15 +61,6 @@ TODO
|
|
| 61 |
|
| 62 |
Moreover, due to its unique hybrid SSM architecture, Zamba2-7B-Instruct achieves extremely low inference latency and rapid generation with a significantly smaller memory footprint than comparable transformer-based models.
|
| 63 |
|
| 64 |
-
<center>
|
| 65 |
-
<img src="https://cdn-uploads.huggingface.co/production/uploads/65c05e75c084467acab2f84a/nHM8bX0y8SWa4zwMSbBi7.png" width="500" alt="Zamba architecture">
|
| 66 |
-
</center>
|
| 67 |
-
|
| 68 |
-
<center>
|
| 69 |
-
<img src="https://cdn-uploads.huggingface.co/production/uploads/65c05e75c084467acab2f84a/qXG8aip6h77LHKjhWfjD5.png" width="500" alt="Zamba architecture">
|
| 70 |
-
</center>
|
| 71 |
-
|
| 72 |
-
|
| 73 |
|
| 74 |
Time to First Token (TTFT) | Output Generation
|
| 75 |
:-------------------------:|:-------------------------:
|
|
|
|
| 61 |
|
| 62 |
Moreover, due to its unique hybrid SSM architecture, Zamba2-7B-Instruct achieves extremely low inference latency and rapid generation with a significantly smaller memory footprint than comparable transformer-based models.
|
| 63 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 64 |
|
| 65 |
Time to First Token (TTFT) | Output Generation
|
| 66 |
:-------------------------:|:-------------------------:
|