Vesper-Zenith-12B/README.md

---
base_model:
- mistralai/Mistral-Nemo-Instruct-2407
- DarkArtsForge/MN-Raven-12B-v1
- Lambent/Arsenic-Shahrazad-12B-v4.4
- Retreatcost/Evertide-RX-12B
- WokeAI/Tankie-DPE-12B-SFT-v2
datasets:
- OccultAI/illuminati_imatrix_v1
language:
- en
library_name: transformers
license: apache-2.0
tags:
- merge
- mergekit
- mistral
- nemo
- della
- creative
- roleplay
- creative-writing
- creative-roleplay
widget:
  - text: "Vesper-Zenith-12B"
    output:
      url: https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/8sWlwh-FjfgmXXys60Av7.png
---

<style>
.vesper-wrapper {
  background: linear-gradient(180deg, #060814 0%, #120b29 50%, #2a0a4a 100%);
  color: #e2e8f0;
  font-family: 'Segoe UI', Roboto, Helvetica, Arial, sans-serif;
  padding: 30px;
  border-radius: 20px;
  border: 1px solid #311b92;
  line-height: 1.6;
  box-shadow: inset 0 0 50px rgba(213, 0, 249, 0.05);
}

.header-container { 
  text-align: center; 
  padding-bottom: 20px; 
}

.vesper-title {
  font-size: 2.5rem;
  font-weight: 900;
  margin: 0;
  letter-spacing: 2px;
  text-transform: uppercase;
}

/* The text gets a gradient from the cyan starlight to the magenta clouds */
.vesper-title span.gradient-text {
  background: linear-gradient(90deg, #00e5ff 0%, #d500f9 50%, #ff4081 100%);
  -webkit-background-clip: text;
  -webkit-text-fill-color: transparent;
  display: inline-block;
  filter: drop-shadow(0 0 12px rgba(213, 0, 249, 0.4));
}

.vesper-subtitle {
  color: #b39ddb; 
  text-transform: uppercase; 
  letter-spacing: 6px; 
  font-size: 0.9rem; 
  margin-top: 10px;
  font-weight: 600;
}

.cosmic-card {
  background: rgba(15, 10, 35, 0.6);
  border-left: 4px solid #d500f9;
  padding: 20px;
  margin: 20px 0;
  border-radius: 0 12px 12px 0;
  box-shadow: 10px 0 30px rgba(213, 0, 249, 0.08);
}

.cyan-card {
  border-left-color: #00e5ff;
  box-shadow: 10px 0 30px rgba(0, 229, 255, 0.08);
}

.lunar-card {
  border-left-color: #ffe57f;
  box-shadow: 10px 0 30px rgba(255, 229, 127, 0.08);
}

.stat-grid {
  display: grid;
  grid-template-columns: repeat(auto-fit, minmax(150px, 1fr));
  gap: 15px;
  margin: 20px 0;
}

.stat-item {
  text-align: center;
  padding: 15px;
  background: rgba(5, 5, 15, 0.8);
  border: 1px solid #4a148c;
  border-radius: 15px;
  box-shadow: 0 4px 10px rgba(0, 0, 0, 0.5);
}

.stat-value {
  display: block;
  font-size: 1.2rem;
  font-weight: bold;
  color: #00e5ff;
  text-shadow: 0 0 8px rgba(0, 229, 255, 0.5);
}

.stat-value.magenta {
  color: #ff4081;
  text-shadow: 0 0 8px rgba(255, 64, 129, 0.5);
}
</style>

<div class="vesper-wrapper">

<div class="header-container">
<h1 class="vesper-title"> 🌕 <span class="gradient-text">VESPER ZENITH 12B</span> ✨ </h1>
<div class="vesper-subtitle">
BEYOND THE ASTRAL VEIL
<img src="https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/8sWlwh-FjfgmXXys60Av7.png" width="100%" style="border-radius: 12px; border: 1px solid #4a148c; margin-bottom: 20px; box-shadow: 0 0 20px rgba(213, 0, 249, 0.2);" alt="Vesper Zenith">
</div>
</div>

<div class="stat-grid">
<div class="stat-item"><span class="stat-value">CREATIVITY</span><span style="font-size: 0.75rem; color: #9fa8da;">UNBOUND</span></div>
<div class="stat-item"><span class="stat-value magenta">ROLEPLAY</span><span style="font-size: 0.75rem; color: #9fa8da;">IMMERSIVE</span></div>
<div class="stat-item"><span class="stat-value">LOGIC</span><span style="font-size: 0.75rem; color: #9fa8da;">ENHANCED</span></div>
</div>

<div class="cosmic-card">
<h3 style="color: #ea80fc; margin-top: 0;">🌌 About The Model</h3>

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

It's recommended to use the `ChatML` template with this model, although it also works with `Mistral Tekken`.

There are some refusals but it's very creative and sadistic when prompted, and it can be ablated or jailbroken if needed.

---

## Merge Details
### Merge Method

This model was merged using the [DELLA](https://arxiv.org/abs/2406.11617) merge method using [mistralai/Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407) as a base.

### Models Merged

The following models were included in the merge:
- [mistralai/Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407)
- [DarkArtsForge/MN-Raven-12B-v1](https://huggingface.co/DarkArtsForge/MN-Raven-12B-v1)
- [Lambent/Arsenic-Shahrazad-12B-v4.4](https://huggingface.co/Lambent/Arsenic-Shahrazad-12B-v4.4)
- [Retreatcost/Evertide-RX-12B](https://huggingface.co/Retreatcost/Evertide-RX-12B)
- [WokeAI/Tankie-DPE-12B-SFT-v2](https://huggingface.co/WokeAI/Tankie-DPE-12B-SFT-v2)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
architecture: MistralForCausalLM
base_model: B:\12B\mistralai--Mistral-Nemo-Instruct-2407
models:
  - model: B:\12B\MN-Raven-12B-v1
    parameters:
      weight: 0.25
      density: 0.9
      epsilon: 0.09
  - model: B:\12B\Lambent--Arsenic-Shahrazad-12B-v4.4
    parameters:
      weight: 0.25
      density: 0.9
      epsilon: 0.09
  - model: B:\12B\Retreatcost--Evertide-RX-12B
    parameters:
      weight: 0.25
      density: 0.9
      epsilon: 0.09
  - model: B:\12B\WokeAI--Tankie-DPE-12B-SFT-v2
    parameters:
      weight: 0.25
      density: 0.9
      epsilon: 0.09
merge_method: della
parameters:  
  lambda: 1.0
  normalize: false
  int8_mask: false
  rescale: true
dtype: float32
out_dtype: bfloat16
tokenizer:
  source: union
chat_template: auto
```

</div>

</div>