---
license: apache-2.0
datasets:
- teknium/openhermes
- trollek/Mouse-Diffusion-Instruct
- trollek/CodeMouse
- trollek/Panoia-v01
- jondurbin/airoboros-3.2
- mlabonne/orpo-dpo-mix-40k
- Magpie-Align/Magpie-Air-300K-Filtered
language:
- en
base_model: trollek/NinjaMouse2-2.5B-v0.2
---
# NinjaMouse2-v0.2-iMat-GGUF
Model: [NinjaMouse2-2.5B-v0.2](https://huggingface.co/trollek/NinjaMouse2-2.5B-v0.2)  
Model creator: [trollek](https://huggingface.co/trollek)
## Quantization notes
Made with llama.cpp b3154, all quants were created with imatrix file based on Exllamav2 default dataset.
# Original model card
# NinjaMouse2-v0.2

A brand spanking new model with a silly name. Brought to you by Anoia, the Goddess of Things That Get Stuck in Drawers, and the psychologial damage of having optic nerves.

With improved image prompting and assistance. 

### Template

It uses the default template of danube2:

```jinja2
<|prompt|>{{instruction}}</s><|answer|>{{response}}</s>
```


### Image prompting

And can be used with the Ollama ComfyUI extension:

[<img src="https://huggingface.co/trollek/NinjaMouse2-2.5B-v0.2/resolve/main/ollama_comfyui.png" width="800px"/>](https://huggingface.co/trollek/NinjaMouse2-2.5B-v0.2/resolve/main/ollama_comfyui.png)

[<img src="https://huggingface.co/trollek/NinjaMouse2-2.5B-v0.2/resolve/main/tophat_cat.png" width="800px"/>](https://huggingface.co/trollek/NinjaMouse2-2.5B-v0.2/resolve/main/tophat_cat.png)


### Ollama

```bash
ollama pull trollek/ninjamouse2:34l-v02-q6_K
ollama pull trollek/ninjamouse2:34l-v02-q5_K_S
ollama pull trollek/ninjamouse2:34l-v02-q4_K_S
```

Trying to fine-tune the chat model even further was a mistake, but a valuable one to make. So was the name. The model is delightful though and does quite well, but will be the last Kung Fu Mouse that I make. It does what I wanted the first one to do, and I am kind of proud of this one considering how many failures it took. 

The rodents and I thank you for your support.