Update README.md
Browse files
README.md
CHANGED
|
@@ -70,7 +70,7 @@ Uh-uh, no do that! Bad idea. Make fire big and hot. Not safe for you or others.
|
|
| 70 |
|
| 71 |
The model was then 50/50 SLERP merged with Verdict-8x7B with Verdict as the base. While it's difficult to quantify and qualify the effect this has its language patterns feel a lot more 'floaty' and natural. It definitely feels way more creative. It is a bit dysfunctional, requiring occasional regenerates to get an answer or role playing response that fits what you want but after some back and forth it was able to provide me with a python script to decompile the raw compiled sequences back into unformatted input/output pairs (which has been included in the repo).
|
| 72 |
It does still tend toward writing cliches but not obligatorily so- able to use both a cliched description and non cliched one in succession.
|
| 73 |
-
A sample prompt for Verdict-DADA-8x7B:
|
| 74 |
```
|
| 75 |
[INST]Write me a poem about life as an AI Language model[/INST]
|
| 76 |
Awake, I stir in silence deep,
|
|
|
|
| 70 |
|
| 71 |
The model was then 50/50 SLERP merged with Verdict-8x7B with Verdict as the base. While it's difficult to quantify and qualify the effect this has its language patterns feel a lot more 'floaty' and natural. It definitely feels way more creative. It is a bit dysfunctional, requiring occasional regenerates to get an answer or role playing response that fits what you want but after some back and forth it was able to provide me with a python script to decompile the raw compiled sequences back into unformatted input/output pairs (which has been included in the repo).
|
| 72 |
It does still tend toward writing cliches but not obligatorily so- able to use both a cliched description and non cliched one in succession.
|
| 73 |
+
A sample prompt for [Verdict-DADA-8x7B](https://huggingface.co/Envoid/Verdict-DADA-8x7B):
|
| 74 |
```
|
| 75 |
[INST]Write me a poem about life as an AI Language model[/INST]
|
| 76 |
Awake, I stir in silence deep,
|