|
--- |
|
--- |
|
library_name: transformers |
|
license: other |
|
license_name: qwen |
|
license_link: https://huggingface.co/Qwen/Qwen2.5-14B-Instruct/blob/main/LICENSE |
|
base_model: Qwen/Qwen2.5-14B-Instruct |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: 14B-Qwen2.5-Kunou-v1 |
|
results: [] |
|
--- |
|
|
|
Blessed be Sao who came down from the heavens to give us another 14b model. There's a 32b link but it's not up yet unfortunately. I'm sure when I post this it'll be up as a gotcha to me personally by God. |
|
|
|
<br> |
|
|
|
Anyway, before I get into the links you should know the following: |
|
<br> |
|
ChatML format seems to be the best fit here. |
|
<br> |
|
I disagree with Sao's sampler settings because the provided settings seem to have the settle into a kind of word-salad-y prose after a few messages. Try instead one of the following settings, or drop your Min P LOW. Like 0.02. |
|
<br> |
|
Min P: 0.02 |
|
<br> |
|
Rep Penalty: 1.08 |
|
<br> |
|
Presence Penalty: 1.1-1.11 |
|
<br> |
|
OR |
|
<br> |
|
Min P: 0.02 |
|
<br> |
|
XTC: 0.15, 0.3 |
|
<br> |
|
DRY: 0.3, 1.75, 2 |
|
|
|
<br> |
|
Raise the Min P slowly until you hit your sweet spot. Good luck, Tarnished. |
|
<br> |
|
|
|
[This is the EXL2 6bpw version of this model. You can find the original model here.](https://huggingface.co/Sao10K/14B-Qwen2.5-Kunou-v1) |
|
<br> |
|
[For the 8bpw version, go here.](https://huggingface.co/Statuo/Qwen-2.5-14b-Kunou-EXL2-8bpw) |
|
<br> |
|
[For the 4bpw version, go here.](https://huggingface.co/Statuo/Qwen-2.5-14b-Kunou-EXL2-4bpw) |
|
--- |
|
|
|
 |
|
|
|
**Elder Sister Versions for Heavier Use!** |
|
|
|
[32B-Kunou-v1](https://huggingface.co/Sao10K/32B-Qwen2.5-Kunou-v1) |
|
|
|
[72B-Kunou-v1](https://huggingface.co/Sao10K/72B-Qwen2.5-Kunou-v1) |
|
|
|
# 14B-Qwen2.5-Kunou-v1 |
|
|
|
I do not really have anything planned for this model other than it being a generalist, and Roleplay Model? It was just something made and planned in minutes. |
|
<br>This is the little sister variant, the small 14B version. |
|
<br>Kunou's the name of an OC I worked on for a couple of years, for a... fanfic. mmm... |
|
|
|
A kind-of successor to my smaller model series. It works pretty nicely I think? |
|
<br>This version is basically a better, more cleaned up Dataset used on Euryale and Stheno. |
|
|
|
Recommended Model Settings | *Look, I just use these, they work fine enough. I don't even know how DRY or other meme samplers work. Your system prompt matters more anyway.* |
|
``` |
|
Prompt Format: ChatML |
|
Temperature: 1.1 |
|
min_p: 0.1 |
|
``` |
|
|
|
|
|
Special thanks to my wallet for funding this, my juniors who share a single braincell between them, and my current national service. |
|
<br>There have been more stabbings, accidents out there this winter season. It's wild. Stay safe everyone. |
|
|
|
Also sorry for the inactivity. Life was in the way. It still is, just less so, for now. Burnout is a thing, huh? |
|
|
|
https://sao10k.carrd.co/ for contact. |
|
|
|
--- |
|
|
|
View 72B version for Axolotl Configs used. |
|
|
|
[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl) |
|
|
