brucethemoose
commited on
Commit
•
1878de7
1
Parent(s):
472adf6
Update README.md
Browse files
README.md
CHANGED
@@ -43,7 +43,7 @@ parameters:
|
|
43 |
dtype: bfloat16
|
44 |
```
|
45 |
|
46 |
-
Tess 1.2 and 1.3 were used because, according to the trainer, they were trained on different datasets: https://migel.substack.com/p/learnings-from-training-tess
|
47 |
|
48 |
I chose not to include other finetunes, such as Dolphin, because they aren't trained on the 200K base.
|
49 |
|
|
|
43 |
dtype: bfloat16
|
44 |
```
|
45 |
|
46 |
+
Tess 1.2 (at a low weight) and 1.3 were used because, according to the trainer, they were trained on different datasets: https://migel.substack.com/p/learnings-from-training-tess
|
47 |
|
48 |
I chose not to include other finetunes, such as Dolphin, because they aren't trained on the 200K base.
|
49 |
|