perlthoughts
commited on
Commit
•
42d3e42
1
Parent(s):
d0ac0a7
Update README.md
Browse files
README.md
CHANGED
@@ -24,7 +24,7 @@ List of all models and merging path is coming soon.
|
|
24 |
|
25 |
## Purpose
|
26 |
|
27 |
-
Merging the "thick"est model weights from mistral models using amazing training methods like
|
28 |
|
29 |
I have spent countless hours studying the latest research papers, attending conferences, and networking with experts in the field. I experimented with different algorithms, tactics, fine-tuned hyperparameters, optimizers,
|
30 |
and optimized code until i achieved the best possible results.
|
|
|
24 |
|
25 |
## Purpose
|
26 |
|
27 |
+
Merging the "thick"est model weights from mistral models using amazing training methods like direct preference optimization (dpo) and reinforced learning.
|
28 |
|
29 |
I have spent countless hours studying the latest research papers, attending conferences, and networking with experts in the field. I experimented with different algorithms, tactics, fine-tuned hyperparameters, optimizers,
|
30 |
and optimized code until i achieved the best possible results.
|