Update README.md
Browse files
README.md
CHANGED
|
@@ -23,9 +23,6 @@ The model has hybrid architecture with Mamba and Attention heads running in para
|
|
| 23 |
This model is ready for commercial use.
|
| 24 |
|
| 25 |
|
| 26 |
-
**[Caution] During generation, the batch size needs to be 1. Our current implementation does not fully support padding of Meta tokens + SWA; this is a work in progress. Training and pre-filling support any batch size.**
|
| 27 |
-
|
| 28 |
-
|
| 29 |
**Model Developer:** NVIDIA
|
| 30 |
|
| 31 |
**Model Dates:** Hymba-1.5B-Base was trained between September 1, 2024 and November 10th, 2024.
|
|
|
|
| 23 |
This model is ready for commercial use.
|
| 24 |
|
| 25 |
|
|
|
|
|
|
|
|
|
|
| 26 |
**Model Developer:** NVIDIA
|
| 27 |
|
| 28 |
**Model Dates:** Hymba-1.5B-Base was trained between September 1, 2024 and November 10th, 2024.
|