Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,11 @@
|
|
1 |
-
---
|
2 |
-
license: llama3.1
|
3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama3.1
|
3 |
+
base_model:
|
4 |
+
- TheFinAI/Fino1-8B
|
5 |
+
---
|
6 |
+
|
7 |
+
Decensored using a custom training script guided by activations, similar to ablation/"abliteration" scripts but not exactly the same approach.
|
8 |
+
|
9 |
+
The training script is released under the MIT license: https://github.com/nkpz/DeLMAT
|
10 |
+
|
11 |
+
The base model says it's for finance, but in my experiences, it's a very good all-purpose reasoning model. Shockingly easy to tune - this was my first try, and there's nothing I would change about it. It does exactly what it's told with a detailed and often entertaining thought process.
|