Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model:
|
| 3 |
+
- cognition-ai/Kevin-32B
|
| 4 |
+
tags:
|
| 5 |
+
- onnx
|
| 6 |
+
- onnxruntime_genai
|
| 7 |
+
- qwen2
|
| 8 |
+
base_model_relation: quantized
|
| 9 |
+
library_name: onnxruntime_genai
|
| 10 |
+
---
|
| 11 |
+
## Kevin-32B
|
| 12 |
+
Kevin (K(ernel D)evin) is a 32B parameter model finetuned to write efficient CUDA kernels.
|
| 13 |
+
|
| 14 |
+
We use KernelBench as our benchmark, and train the model through multi-turn reinforcement learning.
|
| 15 |
+
|
| 16 |
+
For the details, see our blogpost at **https://cognition.ai/blog/kevin-32b**
|
| 17 |
+
|
| 18 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/6490673eb67028b2aa2a6f9f/pjVt_KrR6aWCuWb4GcZuW.png" width="600"/>
|
| 19 |
+
|