← back to catalog · registered 2026-08-22 13:56

pancho101/Uncensored-1b-Creative_Writing_RP-GGUF

pancho101 Llama 1B GGUF second-order 131K ctx
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model.

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/pancho101%2FUncensored-1b-Creative_Writing_RP-GGUF"
Response includes
  • classification m-uncensored
  • files 4
  • hub_downloads_all_time 2,119
  • author_summary 1 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · lifetime
2K
124 last 30d - cooling
Likes
2
Model age
7mo ago
created 2026-02-17

Training datasets

1 of 8 in /datasets

Corpora the author lists in the model card. Datasets tracked in our /datasets catalog carry a category badge linking to the workflow stage. Others open on Hugging Face.

Downloads over time
Now2.2K→from971↑123%
9111.4K1.8K2.3K971 on Feb 182.2K on Oct 11FebAprJunAugOct
Feb 18 → Oct 11 · 73 snapshots · spans 235 days

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Metadata

License
llama3.2
Languages
en es
Tags
transformers gguf llama unsloth uncensored llama-3.2 llama.cpp koboldcpp inference nsfw llama-cpp 1b

Related

Total size
709 MB
Files
4
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-02-17 23:09

Files by quantization

Auxiliary files 4 files 710 MB
Uncensored-1b-Creative_Writing_RP.gguf 709 MB cbf5b431 download
imatrix.dat 1.25 MB 826d94c8 download
.gitattributes 1.69 KB df7526b5 download
README.md 1.57 KB b30bd62f download

README current version from Hugging Face


base_model: carsenk/llama3.2_1b_2025_uncensored_v2
datasets:

  • mlabonne/FineTome-100k
  • microsoft/orca-math-word-problems-200k
  • m-a-p/CodeFeedback-Filtered-Instruction
  • cognitivecomputations/dolphin-coder
  • PawanKrd/math-gpt-4o-200k
  • V3N0M/Jenna-50K-Alpaca-Uncensored
  • FreedomIntelligence/medical-o1-reasoning-SFT
  • Dampfinchen/Creative_Writing_Multiturn-Balanced-8192
    language:
  • en
  • es
    library_name: transformers
    license: llama3.2
    pipeline_tag: text-generation
    tags:
  • llama
  • unsloth
  • uncensored
  • llama-3.2
  • llama.cpp
  • koboldcpp
  • gguf
  • inference
  • nsfw
  • llama-cpp
  • 1b
  • 4-bit
  • rp
  • roleplay
  • not-for-all-audiences

Uncensored 1b Creative Writer RP

Este es un modelo sin censura con siete datasets + uno que he inyectado que se trata de una fusión de alta calidad de diferentes conjuntos de datos de escritura y juego de roles de HuggingFace. Esta versión cuenta con una longitud de secuencia de 8K (tokenizador Llama 3). Asegura que los entrenadores como Axolotl no descarten las muestras. Realizado con el script de https://huggingface.co/xzuyn

Lea la tarjeta del conjunto de datos para obtener más información: https://huggingface.co/datasets/Dampfinchen/Creative_Writing_Multiturn -> Si puede entrenar con una longitud de secuencia de entrada de 16K o más, definitivamente úsela en su lugar.

Tenga en cuenta que este material puede contener todo tipo de datos explícitos problemáticos. No me hago responsable de ello ni lo apruebo. Descargue el material únicamente si conoce la situación legal de los contenidos ficticios escritos de cualquier tipo en su país.

README history 1 version

The author's README evolved over time. Click a version to see its content at that point.

  1. 2026-02-17Duplicate from Novaciano/Uncensored-1b-Creative_Writing_RP-GGUFc05dec61.6 KB
    Loading...

Discussions 2 threads

  1. 2026-09-09Error in llama.cpp when using itopen1 💬#2
    Loading...
  2. 2026-02-18Jejejejeopen1 💬#1
    Loading...
Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Open in Abliteration