Update README.md
Browse files
README.md
CHANGED
|
@@ -14,7 +14,8 @@ Credit to Fernando Fernandes and Eric Hartford for their project [laserRMT](http
|
|
| 14 |
|
| 15 |
This model is a medium-sized MoE implementation based on [cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser](https://huggingface.co/cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser)
|
| 16 |
|
| 17 |
-
|
|
|
|
| 18 |
## Process
|
| 19 |
|
| 20 |
+ The process is outlined in this [notebook](https://github.com/cognitivecomputations/laserRMT/blob/main/examples/laser-dolphin-mixtral-2x7b.ipynb)
|
|
|
|
| 14 |
|
| 15 |
This model is a medium-sized MoE implementation based on [cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser](https://huggingface.co/cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser)
|
| 16 |
|
| 17 |
+
+ The new version shows ~1 point on average.
|
| 18 |
+
|
| 19 |
## Process
|
| 20 |
|
| 21 |
+ The process is outlined in this [notebook](https://github.com/cognitivecomputations/laserRMT/blob/main/examples/laser-dolphin-mixtral-2x7b.ipynb)
|