Edit model card

download.png

This is a fine-tuned LLama3 model.

It was used as a testing and learning ground for me.

It is certainly usable and has been trained to write like a Discord user.

It is good for role-playing (RP) and is uncensored.

If you want to see how the model is supposed to write, do not use a system prompt and you'll find out for yourself.

Have fun, and don't do anything illegal.

-Moritz ☻

Downloads last month
4
Safetensors
Model size
8.03B params
Tensor type
BF16
·
Inference API
Input a message to start chatting with Aculi/Llama3-Sophie.
Model is too large to load in Inference API (serverless). To try the model, launch it on Inference Endpoints (dedicated) instead.

Merge of

Collection including Aculi/Llama3-Sophie