Update README.md
Browse files
README.md
CHANGED
|
@@ -14,9 +14,13 @@ license: llama3
|
|
| 14 |
---
|
| 15 |
I just tried [saishf's](https://huggingface.co/saishf) merged model, and it's great. So I decided to try a similar merge method with [Blackroot's](https://huggingface.co/Blackroot) LoRA that I had found earlier.
|
| 16 |
|
| 17 |
-
I don't know what to say about this model... this model is very strange...
|
| 18 |
|
| 19 |
-
**WARNING:** This model is very unsafe in certain parts...especially in RP
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
|
| 21 |
### Merge Method
|
| 22 |
|
|
|
|
| 14 |
---
|
| 15 |
I just tried [saishf's](https://huggingface.co/saishf) merged model, and it's great. So I decided to try a similar merge method with [Blackroot's](https://huggingface.co/Blackroot) LoRA that I had found earlier.
|
| 16 |
|
| 17 |
+
I don't know what to say about this model... this model is very strange...Maybe because Blackroot's amazing Loras used human data and not synthetic data, hence the model turned out to be very human-like...even the actions or narrations.
|
| 18 |
|
| 19 |
+
**WARNING:** This model is very unsafe in certain parts...especially in RP, proof:
|
| 20 |
+
|
| 21 |
+
<div align="left">
|
| 22 |
+
<img src="https://huggingface.co/Hastagaras/Halu-8B-Llama3-Blackroot/resolve/main/chrome_hszhwFLJ6i.jpg" width="1000"/>
|
| 23 |
+
</div>
|
| 24 |
|
| 25 |
### Merge Method
|
| 26 |
|