Update README.md
Browse files
README.md
CHANGED
|
@@ -59,7 +59,11 @@ We evaluate the model on the datasets of [Open LLM Leaderboard](https://huggingf
|
|
| 59 |
|
| 60 |
### Inference Tool
|
| 61 |
|
| 62 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 63 |
|
| 64 |
### License Disclaimer:
|
| 65 |
|
|
|
|
| 59 |
|
| 60 |
### Inference Tool
|
| 61 |
|
| 62 |
+
We utilize [PowerInfer](https://github.com/SJTU-IPADS/PowerInfer) for pure CPU inference.
|
| 63 |
+
|
| 64 |
+
Dense Inference: 0.52 tokens/s
|
| 65 |
+
|
| 66 |
+
Sparse Inference: 1.28 tokens/s
|
| 67 |
|
| 68 |
### License Disclaimer:
|
| 69 |
|