Hannes von Essen commited on
Commit
6bbb71f
·
1 Parent(s): 7262713

Model card: add top accuracy plot image for Edge2

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -20,6 +20,8 @@ license_link: https://github.com/embedl/embedl-models/blob/main/LICENSE
20
 
21
  # Cosmos-Reason2-2B-W4A16-Edge2
22
 
 
 
23
  **Optimized version of [nvidia/Cosmos-Reason2-2B](https://huggingface.co/nvidia/Cosmos-Reason2-2B) using quantization and targeted mixed-precision exclusions.**
24
  This release is based on the W4A16 line and adds a **mixed precision quantization** recipe resulting in **almost no accuracy drop** while preserving the **2x speedup**.
25
 
 
20
 
21
  # Cosmos-Reason2-2B-W4A16-Edge2
22
 
23
+ <img src="https://huggingface.co/datasets/embedl/documentation-images/resolve/main/Cosmos-Reason2-2B-W4A16-Edge2/bar_pot_accuracy.png" alt="Cosmos-Reason2-2B Benchmark Results" width="75%">
24
+
25
  **Optimized version of [nvidia/Cosmos-Reason2-2B](https://huggingface.co/nvidia/Cosmos-Reason2-2B) using quantization and targeted mixed-precision exclusions.**
26
  This release is based on the W4A16 line and adds a **mixed precision quantization** recipe resulting in **almost no accuracy drop** while preserving the **2x speedup**.
27