add metadata
#2
by
nickname100231
- opened
README.md
CHANGED
|
@@ -1,6 +1,8 @@
|
|
| 1 |
---
|
| 2 |
base_model:
|
| 3 |
- Qwen/QwQ-32B
|
|
|
|
|
|
|
| 4 |
---
|
| 5 |
## Kevin-32B
|
| 6 |
Kevin (K(ernel D)evin) is a 32B parameter model finetuned to write efficient CUDA kernels.
|
|
@@ -9,5 +11,4 @@ We use KernelBench as our benchmark, and train the model through multi-turn rein
|
|
| 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 |
-
|
|
|
|
| 1 |
---
|
| 2 |
base_model:
|
| 3 |
- Qwen/QwQ-32B
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
library_name: transformers
|
| 6 |
---
|
| 7 |
## Kevin-32B
|
| 8 |
Kevin (K(ernel D)evin) is a 32B parameter model finetuned to write efficient CUDA kernels.
|
|
|
|
| 11 |
|
| 12 |
For the details, see our blogpost at **https://cognition.ai/blog/kevin-32b**
|
| 13 |
|
| 14 |
+
<img src="https://cdn-uploads.huggingface.co/production/uploads/6490673eb67028b2aa2a6f9f/pjVt_KrR6aWCuWb4GcZuW.png" width="600"/>
|
|
|