library_name: transformers tags:
- llama-cpp
- koboldcpp
- rp
- roleplay
- nsfw
- uncensored
- not-for-all-audiences base_model: chuanli11/Llama-3.2-3B-Instruct-uncensored license: apache-2.0 datasets:
- MinervaAI/Aesir-Preview language:
- en
- es metrics:
- accuracy
LLAMA 3.2 3B NSFW AESIR UNCENSORED GGUF Note: At the moment this is going to be the only model that I plan to upload from more than 2 trillion parameters since I am only interested in focusing on small models.
Created for an evaluative purpose in quantization Q4_XS to make it lighter, this model is the result of combining the Llama 3.2 model with MinervaAI's Aesir Preview dataset intended for roleplay games.
I don't know at the moment the quality of the result, although it should be good due to the number of parameters.
As for the RAM required to make it run smoothly, I guess that it will require more than 3gb of RAM. If you have less than that, forget it.