Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,25 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
---
|
| 4 |
+
|
| 5 |
+
This repo contains GGUF format model files for [aion-labs/Aion-RP-Llama-3.1-8B](https://huggingface.co/aion-labs/Aion-RP-Llama-3.1-8B).
|
| 6 |
+
|
| 7 |
+
# Model Card
|
| 8 |
+
|
| 9 |
+
## Model Description
|
| 10 |
+
|
| 11 |
+
This is a completely uncensored model that has been trained to excel at roleplaying and creative writing. It can utilize the full 131K context.
|
| 12 |
+
|
| 13 |
+
## Prompt Format
|
| 14 |
+
|
| 15 |
+
The model uses the following prompt format:
|
| 16 |
+
|
| 17 |
+
```
|
| 18 |
+
__SYSTEM__: system message here
|
| 19 |
+
__USER__: user message here
|
| 20 |
+
__ASSISTANT__: assistant message here
|
| 21 |
+
```
|
| 22 |
+
|
| 23 |
+
The model is capable of multi-turn conversations. A system message is not required, however, performance can improve if detailed instructions are provided in a system message.
|
| 24 |
+
|
| 25 |
+
**Important:** the recommended default temperature for this model is 0.7. Setting the temperature to 1.0 can sometimes result in nonsensical output.
|