Safetensors
transformers_zamba2
zamba2
BerenMillidge commited on
Commit
4f8e85c
1 Parent(s): bc722dd

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -0
README.md CHANGED
@@ -72,6 +72,16 @@ Zamba2-1.2B achieves leading and state-of-the-art performance among models of <2
72
 
73
  Zamba2-1.2B's high performance and small inference compute and memory footprint renders it an ideal generalist model for on-device applications.
74
 
 
 
 
 
 
 
 
 
 
 
75
  Time to First Token (TTFT) | Output Generation
76
  :-------------------------:|:-------------------------:
77
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65c05e75c084467acab2f84a/5lpWDLdtPPVAk8COJq7gZ.png) | ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65c05e75c084467acab2f84a/V2tS6eCOGbpKybEoZmOB7.png)
 
72
 
73
  Zamba2-1.2B's high performance and small inference compute and memory footprint renders it an ideal generalist model for on-device applications.
74
 
75
+ <center>
76
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/65c05e75c084467acab2f84a/iu46KgopP6rDrvDpXdlNj.png" width="700" alt="Zamba performance">
77
+ </center>
78
+
79
+
80
+ <center>
81
+ <img src="https://cdn-uploads.huggingface.co/production/uploads/65c05e75c084467acab2f84a/l3U5Z33BY4yUyApbcn7qv.png" width="800" alt="Zamba performance">
82
+ </center>
83
+
84
+
85
  Time to First Token (TTFT) | Output Generation
86
  :-------------------------:|:-------------------------:
87
  ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65c05e75c084467acab2f84a/5lpWDLdtPPVAk8COJq7gZ.png) | ![image/png](https://cdn-uploads.huggingface.co/production/uploads/65c05e75c084467acab2f84a/V2tS6eCOGbpKybEoZmOB7.png)