Update README.md
Browse files
README.md
CHANGED
|
@@ -15,7 +15,10 @@ inference: false
|
|
| 15 |
|
| 16 |
Pygmalion 13b is a dialogue model based on Meta's LLaMA-13b.
|
| 17 |
|
| 18 |
-
This is version 1. It has been fine-tuned using a subset of the data from Pygmalion-6B-v8-pt4,
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
## Applying the XORs
|
| 21 |
|
|
|
|
| 15 |
|
| 16 |
Pygmalion 13b is a dialogue model based on Meta's LLaMA-13b.
|
| 17 |
|
| 18 |
+
This is version 1. It has been fine-tuned using a subset of the data from Pygmalion-6B-v8-pt4,
|
| 19 |
+
for those of you familiar with the project.
|
| 20 |
+
|
| 21 |
+
The current Pygmalion-13b has been trained as a LoRA, then merged down to the base model for distribuition.
|
| 22 |
|
| 23 |
## Applying the XORs
|
| 24 |
|