Update README.md
Browse files
README.md
CHANGED
@@ -24,12 +24,9 @@ Much appreciation goes to the tremendous research effort of **Fernando Fernandes
|
|
24 |
Without their independent research collaboration this model release would not have been possible.
|
25 |
|
26 |
- Fintuned with **SFT**
|
27 |
-
|
28 |
- Aligned with **DPO**
|
29 |
-
|
30 |
- **Using a novel training technique** using less VRAM and prevent less forgetting of the previous model while learning new specific abilities.
|
31 |
It allows to evaluate the no free lunch theorem and make a better choice to optimize it - created by the [LaserRMT research group](https://github.com/cognitivecomputations/laserRMT)
|
32 |
-
|
33 |
- Optimized with **LaserRMT**
|
34 |
|
35 |
# Table of Contents
|
|
|
24 |
Without their independent research collaboration this model release would not have been possible.
|
25 |
|
26 |
- Fintuned with **SFT**
|
|
|
27 |
- Aligned with **DPO**
|
|
|
28 |
- **Using a novel training technique** using less VRAM and prevent less forgetting of the previous model while learning new specific abilities.
|
29 |
It allows to evaluate the no free lunch theorem and make a better choice to optimize it - created by the [LaserRMT research group](https://github.com/cognitivecomputations/laserRMT)
|
|
|
30 |
- Optimized with **LaserRMT**
|
31 |
|
32 |
# Table of Contents
|