Text Generation
Transformers
Safetensors
English
mistral
mergekit
Merge
Not-For-All-Audiences
nsfw
rp
roleplay
text-generation-inference
Update README.md
Browse files
README.md
CHANGED
|
@@ -17,14 +17,4 @@ language:
|
|
| 17 |
---
|
| 18 |
### Prompt Format:
|
| 19 |
- **Extended Alpaca Format** As for exemple from [lemonilia/LimaRP-Mistral-7B-v0.1](https://huggingface.co/lemonilia/LimaRP-Mistral-7B-v0.1).
|
| 20 |
-
Use *### Response: (length = huge)* for exemple, to increase length.
|
| 21 |
-
|
| 22 |
-
### Key features (What I observed):
|
| 23 |
-
- Merely good reasoning.
|
| 24 |
-
- Follows, understand and remember character card well even at 9k~ context. I haven't tested more than 9k yet.
|
| 25 |
-
- Good for multi-turn.
|
| 26 |
-
- Good for creative writing, creating concise stories/texts without repetitiveness or hallucinations on my tests.
|
| 27 |
-
- Follows the character personality well. I tested with a lot and it gave good results.
|
| 28 |
-
- If you like * asterisks rather "quotes" or vice versa, this model is for you. It does not mistakenly use quotes to describe actions.
|
| 29 |
-
|
| 30 |
-
Edit: **I tested with quotes and it works very well for dialogs.**
|
|
|
|
| 17 |
---
|
| 18 |
### Prompt Format:
|
| 19 |
- **Extended Alpaca Format** As for exemple from [lemonilia/LimaRP-Mistral-7B-v0.1](https://huggingface.co/lemonilia/LimaRP-Mistral-7B-v0.1).
|
| 20 |
+
Use *### Response: (length = huge)* for exemple, to increase length.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|