Update README.md
Browse files
README.md
CHANGED
|
@@ -21,7 +21,11 @@ base_model: nvidia/Llama-3_1-Nemotron-51B-Instruct
|
|
| 21 |
|
| 22 |
## Technical Details
|
| 23 |
|
| 24 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 25 |
|
| 26 |
## Special thanks
|
| 27 |
|
|
|
|
| 21 |
|
| 22 |
## Technical Details
|
| 23 |
|
| 24 |
+
Supports a context length of 128k tokens with Rope settings.
|
| 25 |
+
|
| 26 |
+
Distilled version of Llama 3.1-70B-Instruct.
|
| 27 |
+
|
| 28 |
+
For more information, read their blog post [here](https://developer.nvidia.com/blog/advancing-the-accuracy-efficiency-frontier-with-llama-3-1-nemotron-51b/).
|
| 29 |
|
| 30 |
## Special thanks
|
| 31 |
|