Update README.md
Browse files
README.md
CHANGED
|
@@ -20,8 +20,11 @@ I have created a new model architecture that does not require pretraining, and t
|
|
| 20 |
Intel/orca_dpo_pairs (DPO)
|
| 21 |
|
| 22 |
### Surgery and Training
|
|
|
|
| 23 |
viethq188/LeoScorpius-7B-Chat-DPO : 0 ~ 24
|
|
|
|
| 24 |
upstage/SOLAR-10.7B-Instruct-v1.0 : 10 ~ 48
|
|
|
|
| 25 |
Total stacking 62 Layers, qlora and dpo.
|
| 26 |
|
| 27 |
### How to Use
|
|
|
|
| 20 |
Intel/orca_dpo_pairs (DPO)
|
| 21 |
|
| 22 |
### Surgery and Training
|
| 23 |
+
|
| 24 |
viethq188/LeoScorpius-7B-Chat-DPO : 0 ~ 24
|
| 25 |
+
|
| 26 |
upstage/SOLAR-10.7B-Instruct-v1.0 : 10 ~ 48
|
| 27 |
+
|
| 28 |
Total stacking 62 Layers, qlora and dpo.
|
| 29 |
|
| 30 |
### How to Use
|