Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# alpaca-13b-int4
|
| 2 |
+
|
| 3 |
+
LoRA version of alpaca-13b adapted from https://github.com/jooray/alpaca-lora-13b/ using the weights found here https://huggingface.co/samwit/alpaca13B-lora/
|
| 4 |
+
|
| 5 |
+
At the moment this model does not replicate Stanford Alpaca results well enough and should be finetuned for a full 3 epochs on the original dataset. I do not have the resources to do so and I am not aware of anyone who has released a version publicly.
|