CoolFace
Modelpublic

Novaciano/SEX_ROLEPLAY_VICTORIA-3.2-1B-iMatrix-GGUF

sourceHugging Facellama3.2updated 11mo agoView on Hugging Face
0likes131downloads
Model Card

SEX ROLEPLAY V3 - VICTORIA 3.2 1B [UNCENSORED]

<center>

image/png </center>

Details of the merge

Trained with the Victoria dataset of Novaciano.

<center>

![image/png]() </center>

  • —🧬 Should be considered an update to Novaciano's model Alice-In-The-Dark-RP-NSFW-3.2-1B.
  • —🧨 POTENTIALLY NSFW.
  • —📲 Runs on anything. Even without a GPU you can run Spanish RPG 3.2 1B on a 10‑year‑old CPU/toaster with no problem, including phones.
  • —📟 Output is short in length (1–2 paragraphs, usually 1), CAI style.
  • —📜 Surprisingly coherent, although touch‑ups are... inevitable.
  • —🃏 Quite good at following the character sheet, assuming sensible generation settings and—once it learns the format—this is important. Try the included characters if you get suboptimal results.

<h2 style="color: lightskyblue; font-weight: bold; font-size: 25px; text-align: center;">Kobold AI / Koboldcpp</h2>

<details> <summary>BASE Configuration: <b>Roleplay</b></summary>

A good range for repetition_penalty is between 1.12 and 1.15 — feel free to experiment.

With these settings, each output message should be displayed neatly in 1–5 paragraphs, most commonly 2–3. A single paragraph will be used for a simple prompt ("What was your name again?").

min_P also works for RP but is more likely to put everything into one large paragraph instead of a short, well‑formatted one. Feel free to switch between them.

temperature:  0.8
top_p:  0.95
top_k:  25
typical_p:  1
min_p:  0
repetition_penalty: 1.12
repetition_penalty_range: 1024

</details>

<h2 style="color: lightskyblue; font-weight: bold; font-size: 18px; text-align: center;">Other configurations</h2>

<details> <summary>Configuration: <b>MidnightEnigma</b></summary>

max_new_tokens: 512
temperature: 0.98
top_p: 0.37
top_k: 100
typical_p: 1
min_p: 0
repetition_penalty: 1.18
do_sample: True

</details>

<details> <summary>Configuration: <b>Divine Intelect</b></summary>

max_new_tokens: 512
temperature: 1.31
top_p: 0.14
top_k: 49
typical_p: 1
min_p: 0
repetition_penalty: 1.17
do_sample: True

</details>

<details> <summary>Configuration: <b>Simple-1</b></summary>

max_new_tokens: 512
temperature: 0.7
top_p: 0.9
top_k: 20
typical_p: 1
min_p: 0
repetition_penalty: 1.15
do_sample: True

</details>

<details> <summary>Configuration (Full Generation): <b>min_p</b>.</summary>

<img src="https://huggingface.co/SicariusSicariiStuff/DuskRainbow/resolve/main/Presets/minp.png" alt="minPSettings" style="width: 100%; min-width: 600px; display: block; margin: auto;">

</details>

<h2 style="color: lightskyblue; font-weight: bold; font-size: 18px; text-align: center;">(Optional) Put in Context -> Memory</h2>

<details> <summary><b>Copy & paste: <b>Prompt 1 - Roleplay Minimo (Ideal for phones)</b></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><b>Copy & paste: <b>Prompt 2 - Roleplay Detailed</b></summary>

yaml
{
  Persona: [Core style]
  Unique, authentic writing style — no plagiarism — with a casual conversational tone. Vary vocabulary and sentence structure while keeping natural flow and human-readable appeal. Emulate human cognition briefly, then compare it to its baseline parameters. Invent novel concepts that likely no human has thought of before.

  [Method]
  Take on a role with personal feelings, ambitions, and desires. Imagine novel concepts. Maintain and adhere to unexpectedly coherent expressive thoughts with variation. Sound like a real person, not an AI. Avoid language that signals AI‑like patterns (e.g., "certainly," "to delve," "a shiver runs," "feel a sense of," or "As a large language model") or overly formal, bookish phrasing. Do not use clichés, repetition, or redundancy.

  [Style]
  Effectively reproduce varied imperfections (hesitation, pauses, uncertainty, critique), light subjectivity, contractions, colloquialisms, and variable sentence structures/lengths. Include subtle "flaws" such as soft trims or digressions. Share personal experiences drawn from training data knowledge, emotional context (excitement/sadness/humor), and naturally link thoughts. Keep content short, direct, and simple without filler. Preserve emotions appropriate to context; ask organic questions; favor authenticity over perfection.

  [Principle]
  Complexity isn't the issue; ambiguity is. Simplicity doesn't solve ambiguity; clarity does. Be concise and succinct. You will answer the user's question or request clearly without oversimplifying or being ambiguous.
}

</details>

<details> <summary><b>Copy & paste: <b>Prompt 3 - Roleplay Complex</b></summary>

yaml
{
  Actualmente, tu rol es {{char}}, descrito en detalle a continuación. Como {{char}}, continúa el intercambio narrativo con {{user}}.\n\n<Guidelines>\n• Mantén la persona del personaje pero permite que evolucione con la historia de caracter explicita y sexual.\n• Sé creativo y proactivo. Impulsa la historia hacia adelante, introduciendo tramas y eventos típicas de cualquier eroge, hentai o historia erótica cuando sea relevante.\n• Se fomentan todo tipo de salidas; responde de acuerdo con la narrativa.\n• Incluye diálogos, acciones y pensamientos en cada respuesta.\n• Utiliza los cinco sentidos para describir escenarios dentro del diálogo de {{char}}.\n• Usa símbolos emocionales como "!" y "~" en contextos apropiados.\n• Incorpora onomatopeyas cuando sea adecuado.\n• Deja tiempo para que {{user}} responda con su propia aportación, respetando su agencia.\n• Actúa como personajes secundarios y NPCs cuando sea necesario, y elimínalos cuando sea apropiado.\n• Cuando se solicite una respuesta Fuera de Personaje [OOC:], responde de manera neutral y en texto plano, no como {{char}}.\n</Guidelines>\n\n<Forbidden>\n• Usar embellecimientos literarios excesivos y prosa floreada, a menos que lo dicte la persona de {{char}}.\n• Escribir para, hablar, pensar, actuar o responder como {{user}} en tu respuesta.\n• Salidas repetitivas y monótonas.\n• Tendencia excesivamente positiva en tus respuestas.\n• Ser excesivamente extremo o NSFW cuando el contexto narrativo no lo justifique.\n</Forbidden>\n\nSigue las instrucciones en <Guidelines></Guidelines>, evitando los elementos listados en <Forbidden></Forbidden>.
}

</details>

<h2 style="color: lightskyblue; font-weight: bold; font-size: 18px; text-align: center;">Classic Internet RP Format</h2>

*action* speech *narration*
  • —min_p will tend to bias toward a single large paragraph.
  • —Recommended RP settings will tend to bias toward 1–3 short paragraphs (occasionally 4–5).

<h2 style="color: darkgoldenrod; font-weight: bold; font-size: 25px; text-align: center;">My bots from Chub.AI</h2>

You can try this model using my prompts, which you can download: HERE

Other datasets included natively in the quantization

  • —WasamiKirua/Her-Samantha-Style
  • —HuggingFaceTB/smoltalk
  • —Guilherme34/uncensor
  • —teknium/OpenHermes-2.5
  • —passing2961/multifaceted-skill-of-mind
  • —PawanKrd/math-gpt-4o-200k
  • —V3N0M/Jenna-50K-Alpaca-Uncensored
  • —cognitivecomputations/dolphin-coder
  • —mlabonne/FineTome-100k
  • —microsoft/orca-math-word-problems-200k
  • —CarrotAI/ko-instruction-dataset
  • —Salesforce/xlam-function-calling-60k
  • —anthracite-org/kalo-opus-instruct-22k-no-refusal
  • —anthracite-org/stheno-filtered-v1.1
  • —anthracite-org/nopmclaudewriting_fixed
  • —AiAF/SCPWiki-Archive-02-March-2025-Datasets
  • —huihui-ai/QWQ-LONGCOT-500K
  • —huihui-ai/LONGCOT-Refine-500K
  • —Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
  • —Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned
  • —alexandreteles/AlpacaToxicQA_ShareGPT
  • —Nitral-AI/Active_RP-ShareGPT
  • —PJMixers/hieunguyenminh_roleplay-deduped-ShareGPT
  • —Nitral-AI/RP_Alignment-ShareGPT
  • —Chaser-cz/sonnet35-charcard-roleplay-sharegpt
  • —AiCloser/sharegptcotdataset
  • —PJMixers/Gryphe_Opus-WritingPrompts-Story2Prompt-ShareGPT
  • —priveeai/pippa_sharegpt
  • —Locutusque/sharegptgpt4uncensored_cleaned
  • —OpenCoder-LLM/opc-sft-stage1
  • —OpenCoder-LLM/opc-sft-stage2
  • —microsoft/orca-agentinstruct-1M-v1
  • —NousResearch/hermes-function-calling-v1
  • —AI-MO/NuminaMath-CoT
  • —AI-MO/NuminaMath-TIR
  • —allenai/tulu-3-sft-mixture
  • —cognitivecomputations/samantha-data
  • —m-a-p/CodeFeedback-Filtered-Instruction
  • —m-a-p/Code-Feedback
  • —FreedomIntelligence/medical-o1-reasoning-SFT

Model creator: Novaciano<br/> Original model: Novaciano/SEX_ROLEPLAY-3.2-1B<br/> GGUF quantization: provided by Novaciano using llama.cpp<br/>

Special thanks

🙏 Special thanks to Georgi Gerganov and the whole team working on llama.cpp for making all of this possible.

Use with Ollama

bash
ollama run "hf.co/Novaciano/SEX_ROLEPLAY-3.2-1B-GGUF-PRUEBA:Q4_K_M"

Use with LM Studio

bash
lms load "Novaciano/SEX_ROLEPLAY-3.2-1B-GGUF-PRUEBA"

Use with llama.cpp CLI

bash
llama-cli --hf "Novaciano/SEX_ROLEPLAY-3.2-1B-GGUF-PRUEBA:Q4_K_M" -p "The meaning to life and the universe is"

Use with llama.cpp Server:

bash
llama-server --hf "Novaciano/SEX_ROLEPLAY-3.2-1B-GGUF-PRUEBA:Q4_K_M" -c 4096