Update README.md
Browse files
README.md
CHANGED
|
@@ -75,6 +75,11 @@ European Championship => competitions
|
|
| 75 |
|
| 76 |
If you want to use **flash attention** or increase sequence length, please, check the following code:
|
| 77 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 78 |
```python
|
| 79 |
model = GLiNER.from_pretrained("knowledgator/modern-gliner-bi-base-v1.0",
|
| 80 |
_attn_implementation = 'flash_attention_2',
|
|
|
|
| 75 |
|
| 76 |
If you want to use **flash attention** or increase sequence length, please, check the following code:
|
| 77 |
|
| 78 |
+
Firstly, install flash attention and triton packages:
|
| 79 |
+
```bash
|
| 80 |
+
pip install flash-attn triton
|
| 81 |
+
```
|
| 82 |
+
|
| 83 |
```python
|
| 84 |
model = GLiNER.from_pretrained("knowledgator/modern-gliner-bi-base-v1.0",
|
| 85 |
_attn_implementation = 'flash_attention_2',
|