ChatWaifu

ChatWaifu

Not enough ratings
Kachina - Full Eng. Translation/Personality+ vfinal
   
Award
Favorite
Favorited
Unfavorite
Tags: model
File Size
Posted
251.964 MB
17 Dec, 2024 @ 11:21pm
1 Change Note ( view )

Subscribe to download
Kachina - Full Eng. Translation/Personality+ vfinal

Description
**Recommended for use with marco-o1-uncesnsor_ (7_6 Billion Parameters_ 6GB RAM Required) Use Q4KS/Q4KM/Q08, order is based on quality with Q4KS being the lower end_** - 8GB GPU/32GB Ram suggested_

**Use LM Studio for easy model management and importing into Waifu_**

Window Settings for Import of marco-o1 (For n00bs)
Display Name - You Decide
LLM Name - marco-o1-uncensor
GGUF File - link to LLM on your drive. (Waifu will make a copy of this file and create a fileset it can load with ollama in Waifu)
Param Count - 7.6 Billion (Can be found using LM Studio in the model's information.)
Requirement - 6 (This is GB of RAM needed to load in the model. If unsure, give it too much then check the info. after it loads in with Waifu, reload and set correctly.)
Leave the rest alone if you don't know what you're doing.

Translation and rewrite of another pre-existing character model_ I can't ever get the 'emotion reactions' to work on these_ Someone let me know if one ever actually does it lol All the code seems to be correct in the item.json file... but yeah.

Leave questions/comments/requests below_

Genshin Impact Nata, a four-star Rock-element character named Kachina, is super adorable!

The model was not created by me and was downloaded from the Model House_ I am republishing it for my own use_

Model Provider: miHoYo

Model Modifier: Ocean View

Original Mod - steamcommunity_com/sharedfiles/filedetails/?id=3325387581&searchtext By: Jiahong

2 Comments
Chronic-X  [author] 19 Dec, 2024 @ 1:21am 
No problem. There will likely be quite a few more lol I go on these weird binges where I make make character cards. This thing is basically SillyTavern with a live model, although ST is much better for D&D style text adventures with some of the bigger models on OpenRouter or even OpenAI. I need to code an API tool for this so I can connect through OR and actually test them on the really big models.
Riftwind 19 Dec, 2024 @ 12:59am 
Thank you for this, both instructions and uploads. VERY much appreciated.