Commit
·
27ac08b
1
Parent(s):
f8ce208
Update README.md
Browse files
README.md
CHANGED
|
@@ -7,4 +7,7 @@ Llama 2 7B quantized with AutoGPTQ V0.3.0.
|
|
| 7 |
* Group size: 32
|
| 8 |
* Data type: INT4
|
| 9 |
|
| 10 |
-
This model is compatible with the first version of QA-LoRA.
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
* Group size: 32
|
| 8 |
* Data type: INT4
|
| 9 |
|
| 10 |
+
This model is compatible with the first version of QA-LoRA.
|
| 11 |
+
|
| 12 |
+
To fine-tune it with QA-LoRA, follow this tutorial:
|
| 13 |
+
[Fine-tune Quantized Llama 2 on Your GPU with QA-LoRA](https://kaitchup.substack.com/p/fine-tune-quantized-llama-2-on-your)
|