Hasnonname's picture
Update README.md
b470a12 verified
---
license: apache-2.0
base_model:
- unsloth/Mistral-Small-24B-Base-2501
---
![image/webp](https://cdn-uploads.huggingface.co/production/uploads/675a77cf99ca23af9daacccc/KMazK4tkkCrh3kO7N1cJ7.webp)
# MS-24B-Instruct-Mullein-v0
<p><b>V0 note from <a href="https://huggingface.co/finis-est">Severian</a></b>: This instruct variant is tamer and less unhinged than the base version, losing some ability to characterize NPCs but with further improved char/scenario portrayal, a tradeoff of sorts. We couldn't actually decide what to put out, because both are fun and good in their own way.</p>
<p><a href="https://huggingface.co/trashpanda-org/MS-24B-Mullein-v0">Base version</a></p>
<p> Let us know what you think, we're looking forward to seeing people test it.</p>
## Big Thanks
The folks in the trashpanda and ArliAI discords for testing
(In no particular order)
The Allura folks for their [Sugarquill 10k dataset](https://huggingface.co/datasets/allura-org/sugarquill-10k) (which I lightly cleaned for stuff like unicode quotes)
fizz for her [floyd-instruct](https://huggingface.co/datasets/estrogen/floyd-instruct), [woke-identity](https://huggingface.co/datasets/estrogen/woke-identity), and [benchmaxxing (lol)](https://huggingface.co/datasets/estrogen/gpqa-benchmaxxing) datasets
Gryphe for their [Sonnet3.5 RP](https://huggingface.co/datasets/Gryphe/Sonnet3.5-Charcard-Roleplay?not-for-all-audiences=true) and [4o WP](https://huggingface.co/datasets/Gryphe/ChatGPT-4o-Writing-Prompts) datasets, which I heavily filtered for slop
kalo's [Opus-22k](https://huggingface.co/datasets/anthracite-org/kalo-opus-instruct-22k-no-refusal) dataset, which was usable basically OOTB
Norquinal for their [OpenCAI](https://huggingface.co/datasets/Norquinal/OpenCAI) dataset
Dampfinchen for their [Creative Writing Multiturn](https://huggingface.co/datasets/Dampfinchen/Creative_Writing_Multiturn) dataset
The Recursal folks for their [SCP wiki](https://huggingface.co/datasets/recursal/SCP-RECURSAL) dataset
(we also used some other private datasets of our own)
## Reviews
> Base is more unhinged but I see more slops. Would be interesting to see if a merge can balance it out in a good way
>
> Instruct gives me more swipes that I like, it's less horny but it can definitely cook during actual smut
>
> I still like instruct more I think, but I appreciate how unhinged base model can be lol
β€” OMGWTFBBQ
> Hard to send with one hand. What did you feed this model?
β€” Myscell
> It spoke to my body and soul.
β€” Raihanbook
> my cock twitched in interest, 10/10 model
β€” AIELO
> Reroll varies the response by a lot. It's giving Starcannon.
β€” Sam
> Tried the base version with my card. It's just a narrative card and the model makes the character portray right, it also mentions my persona detail often.
β€” Azula
## Just us having fun, don't mind it
Big thanks to the folks in the trashpanda-org discord for testing and sending over some logs!
![image/png](https://cdn-uploads.huggingface.co/production/uploads/674aa6b1f41417ce318abbd9/IyZ4aMG4TeaIrXbojugc8.png)
![image/png](https://cdn-uploads.huggingface.co/production/uploads/674aa6b1f41417ce318abbd9/cMS9UZIi6-U394h2cwTbC.png)
![image/png](https://cdn-uploads.huggingface.co/production/uploads/674aa6b1f41417ce318abbd9/uyN8TqhPhfL0m2QtIvDyB.png)
![image/png](https://cdn-uploads.huggingface.co/production/uploads/674aa6b1f41417ce318abbd9/2vGOohdf0pgEKHyHF6vP6.png)
![image/png](https://cdn-uploads.huggingface.co/production/uploads/674aa6b1f41417ce318abbd9/GW9ofzTSooZPJJ7Dr3mTY.png)
## Merge Details
### Merge Method
This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [unsloth/Mistral-Small-24B-Instruct-2501](https://huggingface.co/unsloth/Mistral-Small-24B-Instruct-2501) as a base.
### Models Merged
The following models were included in the merge:
* [trashpanda-org/MS-24B-Mullein-v0](https://huggingface.co/trashpanda-org/MS-24B-Mullein-v0)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
models:
- model: unsloth/Mistral-Small-24B-Instruct-2501
- model: trashpanda-org/MS-24B-Mullein-v0
parameters:
density: 1
weight: 1
merge_method: ties
base_model: unsloth/Mistral-Small-24B-Instruct-2501
parameters:
normalize: true
dtype: bfloat16
```