Update README.md
Browse files
README.md
CHANGED
|
@@ -2,4 +2,7 @@
|
|
| 2 |
license: mit
|
| 3 |
base_model:
|
| 4 |
- ServiceNow-AI/Apriel-Nemotron-15b-Thinker
|
| 5 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: mit
|
| 3 |
base_model:
|
| 4 |
- ServiceNow-AI/Apriel-Nemotron-15b-Thinker
|
| 5 |
+
---
|
| 6 |
+
Quick and dirty finetune of Apriel, using an improved dataset produced by scoring all replies with a Reward model, then discarding scores <5/5.
|
| 7 |
+
Tried to filter for impersonation as well, but LLama 8B was too stupid.
|
| 8 |
+
Seems to like really low temp and a touch of DRY.
|