Update README.md
Browse files
README.md
CHANGED
|
@@ -128,6 +128,7 @@ In this process, the CNT solar cells generate a tiny amount of power, but when t
|
|
| 128 |
|
| 129 |
## Usage with HuggingFace transformers
|
| 130 |
Model weights were converted to be Hugging Face compatible, with custom modeling files included due to the lack of official support for Mamba2 attention layers.
|
|
|
|
| 131 |
|
| 132 |
To speed up inference, we recommend installing mamba-ssm and flash attention 2.
|
| 133 |
|
|
|
|
| 128 |
|
| 129 |
## Usage with HuggingFace transformers
|
| 130 |
Model weights were converted to be Hugging Face compatible, with custom modeling files included due to the lack of official support for Mamba2 attention layers.
|
| 131 |
+
The attention layer implementation was incorporated from [#32027 PR](https://github.com/huggingface/transformers/pull/32027)
|
| 132 |
|
| 133 |
To speed up inference, we recommend installing mamba-ssm and flash attention 2.
|
| 134 |
|