Update README.md
Browse files
README.md
CHANGED
|
@@ -35,6 +35,11 @@ This is arguably the most successful RPMax model due to how Mistral is already v
|
|
| 35 |
|
| 36 |
v1.2 update completely removes non-creative/RP examples in the dataset and is also an incremental improvement of the RPMax dataset which dedups the dataset even more and better filtering to cutout irrelevant description text that came from card sharing sites.
|
| 37 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 38 |
### Training Details
|
| 39 |
|
| 40 |
* **Sequence Length**: 8192
|
|
|
|
| 35 |
|
| 36 |
v1.2 update completely removes non-creative/RP examples in the dataset and is also an incremental improvement of the RPMax dataset which dedups the dataset even more and better filtering to cutout irrelevant description text that came from card sharing sites.
|
| 37 |
|
| 38 |
+
### Specs
|
| 39 |
+
|
| 40 |
+
* **Context Length**: 128K
|
| 41 |
+
* **Parameters**: 12B
|
| 42 |
+
|
| 43 |
### Training Details
|
| 44 |
|
| 45 |
* **Sequence Length**: 8192
|