Downloads · 30 days
15
3% of all-time downloads
ShyliaSafetensors/VeryWeirdDolphinMix-V1-24B-Heretic
VeryWeirdDolphinMix-V1-24B-Heretic is a text generation model from ShyliaSafetensors. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
Downloads · 30 days
15
3% of all-time downloads
All-time downloads
554
Public
Parameters
23.6B
5.4 MB on disk
Likes
10
Public
Click a slice to open those files.
.safetensors47.1 GB · 100%
From the Hugging Face model README

A three-way DARE-TIES merge combining strong roleplay personality, uncensored thinking capability, and creative prose generation. All in a 24B Mistral-architecture package.
This model merges three complementary 24B models into a single unified experience:
<thinking> reasoning capability and uncensored behavior.The goal was to create a model that handles complex scenes, story-writing and role-play with creativitiy and consistent.
This model can think if these tags used:
<thinking>
</thinking>
merge_method: dare_ties
base_model: coder3101/Cydonia-24B-v4.3-heretic-v4
models:
- model: coder3101/Cydonia-24B-v4.3-heretic-v4
parameters:
weight: 0.40
density: 0.65
- model: DavidAU/Dolphin-Mistral-GLM-4.7-Flash-24B-Venice-Edition-Thinking-Uncensored
parameters:
weight: 0.30
density: 0.60
- model: FlareRebellion/WeirdCompound-v1.7-24b
parameters:
weight: 0.30
density: 0.60
dtype: bfloat16
Merged using mergekit.
| Property | Value |
|---|---|
| Architecture | MistralForCausalLM |
| Parameters | ~24B |
| dtype | bfloat16 |
| Hidden size | 5120 |
| Layers | 40 |
| Attention heads | 32 |
| KV heads | 8 |
| Vocab size | 131072 |
| Context length | 131072 (from Cydonia config) |
These are my recommended settings.
| Setting | Value |
|---|---|
| Temperature | 0.65 - 0.85 |
| Min P | 0.05 - 0.1 |
| Repetition penalty | 1.05 - 1.1 |
| Top P | 0.75 - 0.95 |
| Adaptive-p target | 0.70 - 0.9 |
| Adaptive-p decay | 0.9 |
I recommend some tinkering with these samplers. I personally use Adaptive-P instead of 'DRY repetition penalty' or 'Rep pen'.
Use the Mistral V7 Tekken Template.
This model was processed through the Heretic abliteration engine after merging.
| Metric | Before | After |
|---|---|---|
| Refusal rate | 73 / 100 | 7 / 100 |
| KL Divergence | 0 | 0.0296 |
A KL divergence of 0.0296 is very low - meaning the model's general behavior and coherence were barely affected by the abliteration process.
<thinking>This model is uncensored and intended for adult, research, and creative use. It may produce content that some users find offensive or inappropriate. Use responsibly.