Zyphra
/

Zamba2-1.2B-instruct

Text Generation

Inference Endpoints

Model card Files Files and versions Community

qanthony-z commited on Oct 2

Commit

f8e1f70

•

1 Parent(s): aedddb4

add mt bench fig

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -67,7 +67,7 @@ Zamba2-1.2B-Instruct achieves leading instruction-following and multi-turn chat
 Moreover, due to its unique hybrid SSM architecture, Zamba2-1.2B-Instruct achieves extremely low inference latency and rapid generation with a significantly smaller memory footprint than comparable transformer-based models.
 <center>
-<img src="https://cdn-uploads.huggingface.co/production/uploads/65c05e75c084467acab2f84a/iu46KgopP6rDrvDpXdlNj.png" width="700" alt="Zamba performance">
 </center>

 Moreover, due to its unique hybrid SSM architecture, Zamba2-1.2B-Instruct achieves extremely low inference latency and rapid generation with a significantly smaller memory footprint than comparable transformer-based models.
 <center>
+<img src="https://cdn-uploads.huggingface.co/production/uploads/65bc13717c6ad1994b6619e9/Q82BVdIppSyqPBHYEAjAl.png" width="700" alt="Zamba performance">
 </center>