Llamacpp Quantizations of Ina-v11.1

Ina interprets persona definitions as executable instructions. The model follows <<CHARACTER_DESCRIPTION>> blocks with extremely high fidelity even during 10k–15k token erotic or dark-fiction role-play sessions.

Fine-tuned by BaiAI and Eric Hartford (QuixiAI) using QLoRA + DPO on large volumes of RP logs, creator-voice datasets, and persona modules.

Contributor Credits:

• "Cheshire Cat"
• FitQueen666
• Jaroslavs Samcuks
• Eric Hartford

Using llama.cpp

Original model: https://huggingface.co/QuixiAI/Ina-v11.1

Run them in LM Studio

Run them directly with llama.cpp, or any other llama.cpp based project

Download a file (not the whole branch) from below:

Downloading using huggingface-cli

First, make sure you have hugginface-cli installed:

pip install -U "huggingface_hub[cli]"

Then, you can target the specific file you want:

huggingface-cli download QuixiAI/Ina-v11.1-gguf --include "Ina-v11.1-Q4_K_M.gguf" --local-dir ./

If the model is bigger than 50GB, it will have been split into multiple files. In order to download them all to a local folder, run:

huggingface-cli download QuixiAI/Ina-v11.1-gguf --include "Ina-v11.1-Q8_0/*" --local-dir ./

You can either specify a new local-dir (Ina-v11.1-Q8_0) or download them all in place (./)

Which file should I choose?

A great write up with charts showing various performances is provided by Artefact2 here

The first thing to figure out is how big a model you can run. To do this, you'll need to figure out how much RAM and/or VRAM you have.

If you want your model running as FAST as possible, you'll want to fit the whole thing on your GPU's VRAM. Aim for a quant with a file size 1-2GB smaller than your GPU's total VRAM.

If you want the absolute maximum quality, add both your system RAM and your GPU's VRAM together, then similarly grab a quant with a file size 1-2GB Smaller than that total.

Next, you'll need to decide if you want to use an 'I-quant' or a 'K-quant'.

If you don't want to think too much, grab one of the K-quants. These are in format 'QX_K_X', like Q5_K_M.

If you want to get more into the weeds, you can check out this extremely useful feature chart:

llama.cpp feature matrix

But basically, if you're aiming for below Q4, and you're running cuBLAS (Nvidia) or rocBLAS (AMD), you should look towards the I-quants. These are in format IQX_X, like IQ3_M. These are newer and offer better performance for their size.

These I-quants can also be used on CPU, but will be slower than their K-quant equivalent, so speed vs performance is a tradeoff you'll have to decide.

Credits

I copied Bartowski's model card and made it my own, cheers!