Update README.md
Browse files
README.md
CHANGED
|
@@ -22,7 +22,9 @@ model = LlamaHQQ.from_quantized(model_id)
|
|
| 22 |
|
| 23 |
You can then use the model for text generation or to reproduce the benchmark numbers.
|
| 24 |
|
| 25 |
-
*
|
|
|
|
|
|
|
| 26 |
|
| 27 |
|
| 28 |
|
|
|
|
| 22 |
|
| 23 |
You can then use the model for text generation or to reproduce the benchmark numbers.
|
| 24 |
|
| 25 |
+
*Limitations*:
|
| 26 |
+
-Only supports a single GPU runtime
|
| 27 |
+
-The model is not compatible with HuggingFace's PEFT.
|
| 28 |
|
| 29 |
|
| 30 |
|