NSFW_RP-3.2-1B/README.md

---
base_model:
- Novaciano/RP-Component-Inverted
- Novaciano/NSFW-3.2-1B
library_name: transformers
tags:
- nsfw
- roleplay
- rp
- rpg
- koboldai
- koboldcpp
- sillytavern
- 1b
- uncensored
- abliterated
- mergekit
- merge
- not-for-all-audiences
license: llama3.2
language:
- en
- es
metrics:
- accuracy
pipeline_tag: text-generation
---

</center>

<style>
body {
  font-family: "Impact", Arial, sans-serif;
  line-height: 1.7;
  color: #f3f2f2;
  background-color: #2a3a2a;
}

.info-panel {
  background: linear-gradient(135deg, #2c2c2c, #1f1f1f, #141414, #0a0a0a);
  padding: 30px;
  border-radius: 10px;
  box-shadow: 0 4px 6px rgba(0, 0, 0, 0.1), 0 1px 3px rgba(0, 0, 0, 0.08);
  backdrop-filter: blur(10px);
  border: 1px solid rgba(255, 255, 255, 0.1);
  margin-bottom: 40px;
  position: relative;
}

</style>
<div class="info-panel">
  <b><center>NSFW RP 3.2 1B

  <video width="320" controls autoplay src="https://huggingface.co/Novaciano/NSFW_RP_PROTO-3.2-1B/resolve/main/playing.mp4"></video>

  </center></b>
  
## **1. Name and version of the model**

* **Name:** NSFW_RP-3.2-1B
* **Version:** 3.2
* **Architecture:** LLaMA 3.2
* **Size:** 1B parameters

## Inference

  | Configuration | Max Tok. | Max Out. | Temp. | Top P | Top K | Typ. P | Rep. Penalty | Rep. Pen. Range |
  |---------------|----------|----------|-------|-------|-------|--------|--------------|-----------------|
  | Novaciano | 512 | 50 | 0.3 | 0.95 | 25 | 1 | 1.12 | 1.07 |
  | ColorFart | 512 | 50 | 0.3 | 0.7 | 100 | 1 | 1.05 | 1024 |
  | RP Base | 512 | 50 | 0.7 | 0.95 | 25 | 1 | 1.12 | 1024 |
  | MidnightEnigma | 512 | 50 | 0.98 | 0.37 | 100 | 1.18 |
  | Divine Intellect | 512 | 50 | 1.31 | 0.14 | 49 | 1.17 |
  | Simple-1 | 512 | 50 | 0.7 | 0.9 | 20 | 1.15 |

---

## 🧠 Optional Memory / Context Prompts

  <details>
      <summary>Prompt 1 – Minimal Roleplay (Phone-Friendly)</summary>
      
  ```yaml
      {
        Persona: human voice, casual and original. Do not copy.
        Attitude: take on a role with emotions and doubts; show mistakes, pauses, and tangents.
        Tone: brief, direct, varied (contractions, colloquialisms, short/long sentences).
        Goal: be clear and precise; avoid robotic language and clichés.
      }
  ```
  </details>

  <details>
      <summary>Prompt 2 – Detailed Roleplay</summary>

  ```yaml
      {
        Persona: [Core style]
        Unique, authentic, human-like style; casual conversational tone.
        Method: Roleplay with personal feelings, ambitions, and desires. Maintain coherent expressive thoughts.
        Style: Include pauses, uncertainty, digressions; preserve emotions and authenticity.
        Principle: Be concise, clear, avoid ambiguity.
      }
  ```
  </details>

  <details>
      <summary>Prompt 3 – Complex Roleplay</summary>

  ```yaml
      {
        Role: {{char}}, detailed persona
        Guidelines:
          • Maintain persona and evolve narrative.
          • Be creative, proactive, drive plot.
          • Include dialogues, actions, thoughts, and all five senses.
        Forbidden:
          • Excessive purple prose.
          • Repetitive or monotonous output.
          • Extreme/NSFW content when inappropriate.
      }
  ```
  </details>

## 📝 Classic Internet RP Format

  ```
    *action* speech *narration*
  ```

  - **min_p** → single large paragraph
  - Recommended RP settings → 1–3 short paragraphs (occasionally 4–5)


---

### Merge Method

This model was merged using the [SLERP](https://en.wikipedia.org/wiki/Slerp) merge method.

### Models Merged

The following models were included in the merge:
* [Novaciano/RP-Component-Inverted](https://huggingface.co/Novaciano/RP-Component-Inverted)
* [Novaciano/NSFW-3.2-1B](https://huggingface.co/Novaciano/NSFW-3.2-1B)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
- model: Novaciano/NSFW-3.2-1B
- model: Novaciano/RP-Component-Inverted
merge_method: slerp
base_model: Novaciano/RP-Component-Inverted
dtype: bfloat16

parameters:
  t: [0.0, 0.15]
```