Update README.md
Browse files
README.md
CHANGED
|
@@ -32,6 +32,11 @@ Llama-3.1-8B-ArliAI-RPMax-v1.2 is a variant of the Meta-Llama-3.1-8B model.
|
|
| 32 |
|
| 33 |
v1.2 update is a retrain using 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.
|
| 34 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 35 |
### Training Details
|
| 36 |
|
| 37 |
* **Sequence Length**: 8192
|
|
|
|
| 32 |
|
| 33 |
v1.2 update is a retrain using 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.
|
| 34 |
|
| 35 |
+
### Specs
|
| 36 |
+
|
| 37 |
+
* **Context Length**: 128K
|
| 38 |
+
* **Parameters**: 8B
|
| 39 |
+
|
| 40 |
### Training Details
|
| 41 |
|
| 42 |
* **Sequence Length**: 8192
|