---
license: apache-2.0
base_model:
- Qwen/Qwen2.5-32B-Instruct
tags:
- roleplay
- conversational
language:
- en
---
# Qwen 2.5 32b RP Ink
![image/png](https://cdn-uploads.huggingface.co/production/uploads/634262af8d8089ebaefd410e/1_Zt_OvEW183lmrgidQw8.png)

A roleplay-focused LoRA finetune of Qwen 2.5 32b Instruct. Methodology and hyperparams inspired by [SorcererLM](https://huggingface.co/rAIfle/SorcererLM-8x22b-bf16) and [Slush](https://huggingface.co/crestf411/Q2.5-32B-Slush).  
Yet another model in the Ink series, following in the footsteps of [the Nemo one](https://huggingface.co/allura-org/MN-12b-RP-Ink)

## Testimonials
> whatever I tested was crack [...] It's got some refreshingly good prose, that's for sure

\- TheLonelyDevil

> The NTR is fantastic with this tune, lots of good gooning to be had. [...] Description and scene setting prose flows smoothly in comparison to larger models.

\- TonyTheDeadly

> This 32B handles complicated scenarios well, compared to a lot of 70Bs I've tried. Characters are portrayed accurately.

\- Severian

> From the very limited testing I did, I quite like this. [...] I really like the way it writes.
> Granted, I'm completely shitfaced right now, but I'm pretty sure it's good.

\- ALK

> [This model portrays] my character card almost exactly the way that I write them. It's a bit of a dream to get that with many of the current LLM.

\- ShotMisser64

## Dataset
The worst mix of data you've ever seen. Like, seriously, you do not want to see the things that went into this model. It's bad.

"this is like washing down an adderall with a bottle of methylated rotgut" - inflatebot

## Quants
- [Imatrix GGUFs (thanks, bart!)](https://huggingface.co/bartowski/Qwen2.5-32b-RP-Ink-GGUF)

## Recommended Settings
Chat template: ChatML  
Recommended samplers (not the be-all-end-all, try some on your own!):
- Temp 0.85 / Top P 0.8 / Top A 0.3 / Rep Pen 1.03
- Your samplers can go here! :3

## Hyperparams
### General
- Epochs = 1
- LR = 6e-5
- LR Scheduler = Cosine
- Optimizer = Paged AdamW 8bit
- Effective batch size = 16
### LoRA
- Rank = 16
- Alpha = 32
- Dropout = 0.25 (Inspiration: [Slush](https://huggingface.co/crestf411/Q2.5-32B-Slush))

## Credits
Humongous thanks to the people who created the data. I would credit you all, but that would be cheating ;)  
Big thanks to all Allura members, for testing and emotional support ilya /platonic  
especially to inflatebot who made the model card's image :3  
Another big thanks to all the members of the ArliAI Discord server for testing! All of the people featured in the testimonials are from there :3