Update README.md
Browse files
README.md
CHANGED
|
@@ -57,8 +57,7 @@ tbd.
|
|
| 57 |
pip install transformers==4.37.2 torch==2.1.2 einops==0.7.0
|
| 58 |
|
| 59 |
# be sure to install right flash-attn, we use torch compiled with CUDA 12.1, no ABI, python 3.9, Linux x86_64 architecture
|
| 60 |
-
pip install https://github.com/Dao-AILab/flash-attention/releases/download/v2.5.3/flash_attn-2.5.3+cu122torch2.
|
| 61 |
-
1cxx11abiFALSE-cp39-cp39-linux_x86_64.whl
|
| 62 |
```
|
| 63 |
|
| 64 |
## Running the Code
|
|
|
|
| 57 |
pip install transformers==4.37.2 torch==2.1.2 einops==0.7.0
|
| 58 |
|
| 59 |
# be sure to install right flash-attn, we use torch compiled with CUDA 12.1, no ABI, python 3.9, Linux x86_64 architecture
|
| 60 |
+
pip install https://github.com/Dao-AILab/flash-attention/releases/download/v2.5.3/flash_attn-2.5.3+cu122torch2.1cxx11abiFALSE-cp39-cp39-linux_x86_64.whl
|
|
|
|
| 61 |
```
|
| 62 |
|
| 63 |
## Running the Code
|