Dhruva-hf commited on
Commit
69ebf84
·
verified ·
1 Parent(s): 09e9e35

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +2 -1
README.md CHANGED
@@ -38,9 +38,10 @@ This results in a model that is natively **smaller, faster, and reduces FLOPs**
38
  | **Original ResNet-50** | 0% | 76.13% | 92.86% | 25.56 | 4.12 | ~98 |
39
  | **ModHiFi-Tiny** | **~67%** | **73.85%** | **91.83%** | **8.38** | **1.13** | **~33** |
40
 
 
 
41
  > **Note:** "FLOPs" measures the number of floating-point operations required for a single inference pass. Lower is better for latency and battery life.
42
 
43
- On the hardware we test on (detailed in our [Paper](https://arxiv.org/abs/2511.19566)) we observe speedups of 2.42x on CPUs and 2.38x on GPUs.
44
 
45
  ## ⚠️ Critical Note on Preprocessing & Accuracy
46
 
 
38
  | **Original ResNet-50** | 0% | 76.13% | 92.86% | 25.56 | 4.12 | ~98 |
39
  | **ModHiFi-Tiny** | **~67%** | **73.85%** | **91.83%** | **8.38** | **1.13** | **~33** |
40
 
41
+ On the hardware we test on (detailed in our [Paper](https://arxiv.org/abs/2511.19566)) we observe speedups of **2.42x on CPUs** and **2.38x on GPUs**.
42
+
43
  > **Note:** "FLOPs" measures the number of floating-point operations required for a single inference pass. Lower is better for latency and battery life.
44
 
 
45
 
46
  ## ⚠️ Critical Note on Preprocessing & Accuracy
47