GraySoft
Projects Models About FAQ Contact Download guIDE →
Model Intelligence Sheet

novaciano/sex_roleplay_victoria-3.2-1b-imatrix-gguf overview

!image/png

transformersggufuncensorednsfwrpgrproleplaykoboldcpp1bnot-for-all-audiencestext-generationesendataset:Novaciano/Victoriabase_model:Novaciano/SEX_ROLEPLAY-3.2-1Bbase_model:quantized:Novaciano/SEX_ROLEPLAY-3.2-1Blicense:llama3.2endpoints_compatibleregion:usimatrixconversational
novaciano/sex_roleplay_victoria-3.2-1b-imatrix-gguf visual
Downloads
88
Likes
0
Pipeline
text-generation
Library
transformers
Visibility
Public
Access
Open

Repository Files & Downloads

3 files detected
Direct downloads for all repository files
FileTypeQuantizationSizeLink
SEX_ROLEPLAY-3.2-1B-Q4_K_M-imat.gguf GGUF Q4_K_M 911.20 MB Download
SEX_ROLEPLAY-3.2-1B-Q5_K_M-imat.gguf GGUF Q5_K_M 1.02 GB Download
SEX_ROLEPLAY-3.2-1B-imatrix.gguf GGUF 1.27 MB Download

Model Details Live

Model Slug
novaciano/sex_roleplay_victoria-3.2-1b-imatrix-gguf
Author
Novaciano
Pipeline Task
text-generation
Library
transformers
Created
2025-10-21
Last Modified
2025-10-21
Gated
No
Private
No
HF SHA
a1b1b2838a24f823665d361b9e340c3bcfa54bbd
License
llama3.2
Language
es, en
Base Model
Novaciano/SEX_ROLEPLAY-3.2-1B

Metadata Inspector

Normalized metadata (stored in metadata_json)
{
  "metadata": {},
  "card_data": {
    "base_model": "Novaciano/SEX_ROLEPLAY-3.2-1B",
    "library_name": "transformers",
    "datasets": [
      "Novaciano/Victoria"
    ],
    "tags": [
      "gguf",
      "uncensored",
      "nsfw",
      "rpg",
      "rp",
      "roleplay",
      "koboldcpp",
      "1b",
      "not-for-all-audiences"
    ],
    "license": "llama3.2",
    "language": [
      "es",
      "en"
    ],
    "pipeline_tag": "text-generation",
    "frontmatter": {
      "base_model": "Novaciano/SEX_ROLEPLAY-3.2-1B",
      "library_name": "transformers",
      "datasets": [
        "Novaciano/Victoria"
      ],
      "tags": [
        "gguf",
        "uncensored",
        "nsfw",
        "rpg",
        "rp",
        "roleplay",
        "koboldcpp",
        "1b",
        "not-for-all-audiences"
      ],
      "license": "llama3.2",
      "language": [
        "es",
        "en"
      ],
      "pipeline_tag": "text-generation"
    },
    "hero_image_url": "https://huggingface.co/SicariusSicariiStuff/Dusk_Rainbow/resolve/main/Presets/min_p.png",
    "summary": "!image/png",
    "quick_links": [],
    "benchmark_table_html": "",
    "readme_markdown": "---\nbase_model: Novaciano/SEX_ROLEPLAY-3.2-1B\nlibrary_name: transformers\ndatasets:\n- Novaciano/Victoria\ntags:\n- gguf\n- uncensored\n- nsfw\n- rpg\n- rp\n- roleplay\n- koboldcpp\n- 1b\n- not-for-all-audiences\nlicense: llama3.2\nlanguage:\n- es\n- en\npipeline_tag: text-generation\n---\n\n# SEX ROLEPLAY V3 - VICTORIA 3.2 1B [UNCENSORED]\n\n<center>\n  \n  ![image/png](https://i.ibb.co/bMrwyKSv/DR6j33-XJIQWb48-Jc-Gv-Bu-Pamg-10i-Vq-Cg2-DJMa-UM.webp)\n</center>\n\n\n## Details of the merge\n\nTrained with the Victoria dataset of Novaciano.\n\n<center>\n  \n  ![image/png]()\n</center>\n\n- 🧬 Should be considered an update to Novaciano's model **Alice-In-The-Dark-RP-NSFW-3.2-1B**.  \n- 🧨 **POTENTIALLY NSFW**.  \n- 📲 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.  \n- 📟 Output is **short in length** (1–2 paragraphs, usually 1), CAI style.  \n- 📜 Surprisingly coherent, although touch‑ups are... **inevitable**.  \n- 🃏 **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.\n  \n---\n\n<h2 style=\"color: lightskyblue; font-weight: bold; font-size: 25px; text-align: center;\">Kobold AI / Koboldcpp</h2>\n\n<details>\n<summary>BASE Configuration: <b>Roleplay</b></summary>\n  \nA good range for repetition_penalty is between **1.12 and 1.15** — feel free to experiment.\n\nWith 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?\").\n\n**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.\n\n```\ntemperature:  0.8\ntop_p:  0.95\ntop_k:  25\ntypical_p:  1\nmin_p:  0\nrepetition_penalty: 1.12\nrepetition_penalty_range: 1024\n```\n\n</details>\n\n<h2 style=\"color: lightskyblue; font-weight: bold; font-size: 18px; text-align: center;\">Other configurations</h2>\n\n<details>\n<summary>Configuration: <b>MidnightEnigma</b></summary>\n\n```\nmax_new_tokens: 512\ntemperature: 0.98\ntop_p: 0.37\ntop_k: 100\ntypical_p: 1\nmin_p: 0\nrepetition_penalty: 1.18\ndo_sample: True\n```\n\n</details>\n\n<details>\n<summary>Configuration: <b>Divine Intelect</b></summary>\n\n```\nmax_new_tokens: 512\ntemperature: 1.31\ntop_p: 0.14\ntop_k: 49\ntypical_p: 1\nmin_p: 0\nrepetition_penalty: 1.17\ndo_sample: True\n```\n\n</details>\n\n<details>\n<summary>Configuration: <b>Simple-1</b></summary>\n\n```\nmax_new_tokens: 512\ntemperature: 0.7\ntop_p: 0.9\ntop_k: 20\ntypical_p: 1\nmin_p: 0\nrepetition_penalty: 1.15\ndo_sample: True\n```\n</details>\n\n<details>\n<summary>Configuration (Full Generation): <b>min_p</b>.</summary>\n\n<img src=\"https://huggingface.co/SicariusSicariiStuff/Dusk_Rainbow/resolve/main/Presets/min_p.png\" alt=\"min_P_Settings\" style=\"width: 100%; min-width: 600px; display: block; margin: auto;\">\n\n</details>\n\n<h2 style=\"color: lightskyblue; font-weight: bold; font-size: 18px; text-align: center;\">(Optional) Put in Context -> Memory</h2>\n\n<details>\n<summary><b>Copy & paste: <b>Prompt 1 - Roleplay Minimo (Ideal for phones)</b></summary>\n\n```yaml\n{\nPersona: human voice, casual and original. Do not copy.\n\nAttitude: take on a role with emotions and doubts; show mistakes, pauses, and tangents.\n\nTone: brief, direct, varied (contractions, colloquialisms, short/long sentences).\n\nGoal: be clear and precise; avoid robotic language and clichés.\n}\n```\n</details>\n\n<details>\n<summary><b>Copy & paste: <b>Prompt 2 - Roleplay Detailed</b></summary>\n\n```yaml\n{\n  Persona: [Core style]\n  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.\n\n  [Method]\n  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.\n\n  [Style]\n  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.\n\n  [Principle]\n  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.\n}\n  ```\n\n</details>\n\n<details>\n<summary><b>Copy & paste: <b>Prompt 3 - Roleplay Complex</b></summary>\n\n```yaml\n{\n  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>.\n}\n```\n\n</details>\n\n<h2 style=\"color: lightskyblue; font-weight: bold; font-size: 18px; text-align: center;\">Classic Internet RP Format</h2>\n\n```\n*action* speech *narration*\n```\n\n- **min_p** will tend to bias toward a **single large paragraph**.  \n- Recommended RP settings will tend to bias toward **1–3 short paragraphs** (occasionally 4–5).\n  \n---\n\n<h2 style=\"color: darkgoldenrod; font-weight: bold; font-size: 25px; text-align: center;\">My bots from Chub.AI</h2>\n\n**You can try this model using my prompts, which you can download:**  [HERE](https://chub.ai/users/Novaciano)\n\n---\n\n### Other datasets included natively in the quantization\n- WasamiKirua/Her-Samantha-Style\n- HuggingFaceTB/smoltalk\n- Guilherme34/uncensor\n- teknium/OpenHermes-2.5\n- passing2961/multifaceted-skill-of-mind\n- PawanKrd/math-gpt-4o-200k\n- V3N0M/Jenna-50K-Alpaca-Uncensored\n- cognitivecomputations/dolphin-coder\n- mlabonne/FineTome-100k\n- microsoft/orca-math-word-problems-200k\n- CarrotAI/ko-instruction-dataset\n- Salesforce/xlam-function-calling-60k\n- anthracite-org/kalo-opus-instruct-22k-no-refusal\n- anthracite-org/stheno-filtered-v1.1\n- anthracite-org/nopm_claude_writing_fixed\n- AiAF/SCPWiki-Archive-02-March-2025-Datasets\n- huihui-ai/QWQ-LONGCOT-500K\n- huihui-ai/LONGCOT-Refine-500K\n- Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned\n- Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleaned\n- alexandreteles/AlpacaToxicQA_ShareGPT\n- Nitral-AI/Active_RP-ShareGPT\n- PJMixers/hieunguyenminh_roleplay-deduped-ShareGPT\n- Nitral-AI/RP_Alignment-ShareGPT\n- Chaser-cz/sonnet35-charcard-roleplay-sharegpt\n- AiCloser/sharegpt_cot_dataset\n- PJMixers/Gryphe_Opus-WritingPrompts-Story2Prompt-ShareGPT\n- priveeai/pippa_sharegpt\n- Locutusque/sharegpt_gpt4_uncensored_cleaned\n- OpenCoder-LLM/opc-sft-stage1\n- OpenCoder-LLM/opc-sft-stage2\n- microsoft/orca-agentinstruct-1M-v1\n- NousResearch/hermes-function-calling-v1\n- AI-MO/NuminaMath-CoT\n- AI-MO/NuminaMath-TIR\n- allenai/tulu-3-sft-mixture\n- cognitivecomputations/samantha-data\n- m-a-p/CodeFeedback-Filtered-Instruction\n- m-a-p/Code-Feedback\n- FreedomIntelligence/medical-o1-reasoning-SFT\n\n---\n\n**Model creator:** [Novaciano](https://huggingface.co/Novaciano)<br/>\n**Original model**: [Novaciano/SEX_ROLEPLAY-3.2-1B](https://huggingface.co/Novaciano/SEX_ROLEPLAY-3.2-1B)<br/>\n**GGUF quantization:** provided by [Novaciano](https:/huggingface.co/Novaciano) using `llama.cpp`<br/>\n\n## Special thanks\n🙏 Special thanks to [Georgi Gerganov](https://github.com/ggerganov) and the whole team working on [llama.cpp](https://github.com/ggerganov/llama.cpp/) for making all of this possible.\n\n## Use with Ollama\n```bash\nollama run \"hf.co/Novaciano/SEX_ROLEPLAY-3.2-1B-GGUF-PRUEBA:Q4_K_M\"\n```\n\n## Use with LM Studio\n```bash\nlms load \"Novaciano/SEX_ROLEPLAY-3.2-1B-GGUF-PRUEBA\"\n```\n\n## Use with llama.cpp CLI\n```bash\nllama-cli --hf \"Novaciano/SEX_ROLEPLAY-3.2-1B-GGUF-PRUEBA:Q4_K_M\" -p \"The meaning to life and the universe is\"\n```\n\n## Use with llama.cpp Server:\n```bash\nllama-server --hf \"Novaciano/SEX_ROLEPLAY-3.2-1B-GGUF-PRUEBA:Q4_K_M\" -c 4096\n```",
    "related_quantizations": []
  },
  "tags": [
    "transformers",
    "gguf",
    "uncensored",
    "nsfw",
    "rpg",
    "rp",
    "roleplay",
    "koboldcpp",
    "1b",
    "not-for-all-audiences",
    "text-generation",
    "es",
    "en",
    "dataset:Novaciano/Victoria",
    "base_model:Novaciano/SEX_ROLEPLAY-3.2-1B",
    "base_model:quantized:Novaciano/SEX_ROLEPLAY-3.2-1B",
    "license:llama3.2",
    "endpoints_compatible",
    "region:us",
    "imatrix",
    "conversational"
  ],
  "likes": 0,
  "downloads": 88,
  "gated": false,
  "private": false,
  "last_modified": "2025-10-21T16:19:03.000Z",
  "created_at": "2025-10-21T15:18:46.000Z",
  "pipeline_tag": "text-generation",
  "library_name": "transformers"
}
Source payload excerpt (from Hugging Face API)
{
  "_id": "68f7a4561281e08db4085cb1",
  "id": "Novaciano/SEX_ROLEPLAY_VICTORIA-3.2-1B-iMatrix-GGUF",
  "modelId": "Novaciano/SEX_ROLEPLAY_VICTORIA-3.2-1B-iMatrix-GGUF",
  "sha": "a1b1b2838a24f823665d361b9e340c3bcfa54bbd",
  "createdAt": "2025-10-21T15:18:46.000Z",
  "lastModified": "2025-10-21T16:19:03.000Z",
  "author": "Novaciano",
  "downloads": 88,
  "likes": 0,
  "gated": false,
  "private": false,
  "pipeline_tag": "text-generation",
  "library_name": "transformers",
  "siblings_count": 5
}