Update README.md
Browse files
README.md
CHANGED
|
@@ -7,4 +7,7 @@ Kevin (K(ernel D)evin) is a 32B parameter model finetuned to write efficient CUD
|
|
| 7 |
|
| 8 |
We use KernelBench as our benchmark, and train the model through multi-turn reinforcement learning.
|
| 9 |
|
| 10 |
-
For the details, see our blogpost at **https://cognition.ai/blog/kevin-32b**
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
|
| 8 |
We use KernelBench as our benchmark, and train the model through multi-turn reinforcement learning.
|
| 9 |
|
| 10 |
+
For the details, see our blogpost at **https://cognition.ai/blog/kevin-32b**
|
| 11 |
+
|
| 12 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/6490673eb67028b2aa2a6f9f/pjVt_KrR6aWCuWb4GcZuW.png" width="600"/>
|
| 13 |
+
|