VictorSanh
commited on
Commit
•
6e13295
1
Parent(s):
2c25217
Update README.md
Browse files
README.md
CHANGED
@@ -247,7 +247,7 @@ Flash attention 2 support is available both for `idefics2-8b-base` and `idefics2
|
|
247 |
|
248 |
<details><summary>Click to expand.</summary>
|
249 |
|
250 |
-
4-bit AWQ-quantized versions of the checkpoints are also available and allow module fusing for accelerated inference. First make sure you install the Auto-AWQ library with `pip install autoawq`. Also make sure that this [fix] is integrated into your installation.
|
251 |
|
252 |
```diff
|
253 |
+ from transformers import AwqConfig
|
|
|
247 |
|
248 |
<details><summary>Click to expand.</summary>
|
249 |
|
250 |
+
4-bit AWQ-quantized versions of the checkpoints are also available and allow module fusing for accelerated inference. First make sure you install the Auto-AWQ library with `pip install autoawq`. Also make sure that this [fix](https://github.com/casper-hansen/AutoAWQ/pull/444) is integrated into your installation.
|
251 |
|
252 |
```diff
|
253 |
+ from transformers import AwqConfig
|