Update README.md
Browse files
README.md
CHANGED
|
@@ -22,7 +22,7 @@ Turn out you do not need to depend on just reasoning models (r1, o1, o3, etc) to
|
|
| 22 |
|
| 23 |
It has many goals in mind, but mainly:
|
| 24 |
- enabling faster synthetic reasoning dataset generation, since we're using a small model here (smaller than r1, etc) so faster to do inference on, thus easier to scale
|
| 25 |
-
-
|
| 26 |
- converting any non-reasoning model output/datasets to a reasoning synthetic dataset when used as input
|
| 27 |
|
| 28 |
So far, current proof of concept managed to check the boxes for 1 and 3, and I plan on scaling this more as:
|
|
|
|
| 22 |
|
| 23 |
It has many goals in mind, but mainly:
|
| 24 |
- enabling faster synthetic reasoning dataset generation, since we're using a small model here (smaller than r1, etc) so faster to do inference on, thus easier to scale
|
| 25 |
+
- distill on synthetic traces for out of domain non-verifiable problems
|
| 26 |
- converting any non-reasoning model output/datasets to a reasoning synthetic dataset when used as input
|
| 27 |
|
| 28 |
So far, current proof of concept managed to check the boxes for 1 and 3, and I plan on scaling this more as:
|