macadeliccc
commited on
Commit
•
0ece180
1
Parent(s):
7a42420
Update README.md
Browse files
README.md
CHANGED
@@ -14,6 +14,8 @@ A 2x7b configuration offers better performance than a standard 7b model even if
|
|
14 |
|
15 |
If this 2x7b model is loaded in 4 bit the hellaswag score is .8270 which is higher than the base model achieves on its own in full precision.
|
16 |
|
|
|
|
|
17 |
## Prompt Format
|
18 |
|
19 |
This model follows the same prompt format as the aforementioned model.
|
|
|
14 |
|
15 |
If this 2x7b model is loaded in 4 bit the hellaswag score is .8270 which is higher than the base model achieves on its own in full precision.
|
16 |
|
17 |
+
The process is outlined in this [notebook](https://github.com/cognitivecomputations/laserRMT/blob/main/examples/laser-dolphin-mixtral-2x7b.ipynb)
|
18 |
+
|
19 |
## Prompt Format
|
20 |
|
21 |
This model follows the same prompt format as the aforementioned model.
|