Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
The LLaMA based Pygmalion-7b model:
|
| 2 |
+
|
| 3 |
+
https://huggingface.co/PygmalionAI/pygmalion-7b
|
| 4 |
+
|
| 5 |
+
Merged alongside lmsys's Vicuna v1.1 deltas:
|
| 6 |
+
|
| 7 |
+
https://huggingface.co/lmsys/vicuna-13b-delta-v1.1
|
| 8 |
+
|
| 9 |
+
This merge was done using an weighted average merge strategy, and the end result is a model composed of:
|
| 10 |
+
|
| 11 |
+
Pygmalion-7b [60%] + LLaMA Vicuna v1.1 [40%]
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
This was done under request, but the end result is intended to lean heavily towards Pygmalion's chatting + RP tendencies, and to inherit some of Vicuna's Assistant / Instruct / Helpful properties.
|
| 15 |
+
|
| 16 |
+
Due to the influence of Pygmalion, this model will very likely generate content that is considered NSFW.
|
| 17 |
+
|
| 18 |
+
The specific prompting is unknown, but try Pygmalion's prompt styles first, then a mix of the two to see what brings most interesting results.
|
| 19 |
+
|
| 20 |
+
Treat this as a normal HF Transformers model.
|