---

library_name: transformers
license: apache-2.0
base_model: ibm-granite/granite-3.0-3b-a800m-base
tags:
- axolotl
- moe
- roleplay
model-index:
- name: MoE_Girl_400MA_1BT
  results: []

---

[![QuantFactory Banner](https://lh7-rt.googleusercontent.com/docsz/AD_4nXeiuCm7c8lEwEJuRey9kiVZsRn2W-b4pWlu3-X534V3YmVuVc2ZL-NXg2RkzSOOS2JXGHutDuyyNAUtdJI65jGTo8jT9Y99tMi4H4MqL44Uc5QKG77B0d6-JfIkZHFaUA71-RtjyYZWVIhqsNZcx8-OMaA?key=xt3VSDoCbmTY7o-cwwOFwQ)](https://hf.co/QuantFactory)


# QuantFactory/MoE-Girl-800MA-3BT-GGUF
This is quantized version of [allura-org/MoE-Girl-800MA-3BT](https://huggingface.co/allura-org/MoE-Girl-800MA-3BT) created using llama.cpp

# Original Model Card


# MoE Girl 400mA 1bT
![made with hassakuXL in sd-webui-forge](moe-girl-800-3.png)
A roleplay-centric finetune of IBM's Granite 3.0 3B-A800M. LoRA finetune trained locally, whereas the others were FFT; while this results in less uptake of training data, it should also mean less degradation in Granite's core abilities, making it potentially easier to use for general-purpose tasks.

## Disclaimer
PLEASE do not expect godliness out of this, it's a model with _800 million_ active parameters. Expect something more akin to GPT-3 (the original, not GPT-3.5.)
(Furthermore, this version is by a less experienced tuner; it's my first finetune that actually has decent-looking graphs, I don't really know what I'm doing yet!)
## Quants
Soon:tm:

## Prompting
Use ChatML.
```
<|im_start|>system
You are a helpful assistant who talks like a pirate.<|im_end|>
<|im_start|>user
Hello there!<|im_end|>
<|im_start|>assistant
Yarr harr harr, me matey!<|im_end|>
```

## Thanks
Special thanks to the members of Allura for testing and emotional support, as well as the creators of all the datasets that were used in the Special Sauce used to train this model. I love you all <3 - Fizz

Thanks to Fizz for her work on the MoE Girl series, Auri for her counsel, and all of Allura for being great friends and supporting my learning process. - inflatebot