Commit
·
4009b43
1
Parent(s):
b735900
Update README.md
Browse files
README.md
CHANGED
|
@@ -2,4 +2,7 @@
|
|
| 2 |
license: mit
|
| 3 |
datasets:
|
| 4 |
- mlabonne/guanaco-llama2
|
| 5 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: mit
|
| 3 |
datasets:
|
| 4 |
- mlabonne/guanaco-llama2
|
| 5 |
+
---
|
| 6 |
+
# Finetuning Llama2 7b on 1000 samples from the Guanaco dataset, using QLoRA - quantization + low rank adaptation.
|
| 7 |
+
|
| 8 |
+
The Llama2 model from Meta has several variants. The smallest one containing 7 billion parameters has been finetuned here.
|