|
--- |
|
language: |
|
- en |
|
license: apache-2.0 |
|
tags: |
|
- safetensors |
|
- mixtral |
|
--- |
|
|
|
I prefer this one instead of v1 since it's a bit more creative and _smart_, understand the story better. This use some different models from the v1 but perform very close to it (I guess since I used the same model for the base?). And yeah, I'm using this as daily model for RP (llama 3 is smart but not creative enough for RP, I think because lack of RP and _ERP_ data in their training set? idk.) |
|
|
|
|
|
Testing done. |
|
|
|
It performs really well in complex scenario and follows the character card quite well. The char card and previous message can affect a lot to the next reply style. |
|
|
|
The main idea is instead of _merging_ models to create new model, I try to put these best model into mixtral so it can work together. And the result is good, every model has its uniqueness and strength. |
|
|
|
Downside? it only support 8k (8192) context length... |
|
|
|
Alpaca prompting format. |
