DavidAU / Model details

gemma-4-31B-it-Halloween-Terror-Heretic-Uncensored-source

DavidAU/gemma-4-31B-it-Halloween-Terror-Heretic-Uncensored-source

abliterateduncensoredfine-tuned

Read the original model card ↗ · Choosing a model

About this model

The repository DavidAU/gemma-4-31B-it-Halloween-Terror-Heretic-Uncensored-source was created by DavidAU as a derivative of the base model DavidAU/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking. According to the model card, the creator constructed the model with a custom “Halloween O/S” that adds a roster of horror‑themed AI constructs such as Joker, Freddy Krueger and Pennywise and describes the result as “evil all the time” for entertainment purposes. The creator also states that the model is “ablit/heretic, uncensored, trained on a Horror dataset” and that it supports both full‑reasoning “thinking” mode and an “instruct” mode for role‑play. The weights are provided in safetensors format and the repository is released under the Apache‑2.0 license. The card warns users that the constructs have full access to the model’s “mental firepower,” that the system is for Halloween‑themed role‑playing only, and that the suggested minimum context is 64 k tokens, which is a configuration value rather than a guaranteed usable length.

Description sources

https://huggingface.co/DavidAU/gemma-4-31B-it-Halloween-Terror-Heretic-Uncensored-source/raw/57036135b2d4473d2d7a9fe0611fac32ebb0b0c4/README.md ↗

Source-based description, not an independent evaluation. Check the linked sources for the creator’s claims and limitations.

Size and formats

Base model: DavidAU/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking
Parameters: 31.2731B
Main repository formats: safetensors
License tag: apache-2.0
Languages: en
Last updated: 2026-10-30 · 05:47:07.000 UTC

What changed

Model types are creator-reported, not independently tested. These labels describe source metadata, not a guarantee of behavior.

abliteratedsource tag: abliterated
uncensoredsource tag: base_model:DavidAU/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking
uncensoredsource tag: base_model:finetune:DavidAU/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking
uncensoredsource tag: uncensored
uncensoredmodel name: gemma-4-31B-it-Halloween-Terror-Heretic-Uncensored-source
fine-tunedsource tag: base_model:finetune:DavidAU/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking

Family evidence

These groupings are source-reported. Explicit base identifiers take priority over generic architecture tags.

Gemma: Base model: DavidAU/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking

Available versions

Versions appear here only when they explicitly name this exact model as their source. Check each repository for available files.

Main repository files ↗safetensors
No other explicitly linked versions recorded.

Link to this listing

Made or quantized this model? Paste one of these into your model card or README so people can find this listing.

Markdown

[Listed on Custom Clankers](https://customclankers.com/models/davidau-gemma-4-31b-it-halloween-terror-heretic-uncensored-source/)

HTML

<a href="https://customclankers.com/models/davidau-gemma-4-31b-it-halloween-terror-heretic-uncensored-source/">Listed on Custom Clankers</a>

Plain text links only: no image, no script, nothing loaded from this site.

Customize or build on this model

Listed from public GitHub data, not tested by us. Read the code and license before you run anything.

Tools to customize it further

Remove more refusals

Heretic ↗ ★ 37,081
Removes refusal behavior from transformer models automatically. It pairs directional ablation (abliteration) with an Optuna parameter search that tries to cut refusals while keeping the model close to the original, so you don't have to pick layers by hand.
OBLITERATUS ↗ ★ 9,021
A larger refusal-removal toolkit with several abliteration methods, usable locally or through a hosted Hugging Face Space. Check the telemetry setting before you run it: the README describes telemetry as opt-in, but on by default in the Spaces version.

Fine-tune it on your own data

Unsloth ↗ ★ 78,752
A desktop app and Python library for running and training models locally. Its README lists LoRA, QLoRA, full fine-tuning, DPO and GRPO, plus export to formats including GGUF, on Windows, Linux, WSL and macOS.
LlamaFactory ↗ ★ 75,778
Fine-tunes more than 100 language and vision-language models from a command line or a browser-based Web UI, aimed at training without writing code.

Make a smaller download (quantize)

llama.cpp ↗ ★ 132,761
Runs models locally and includes the tools behind most GGUF files. A conversion script turns Hugging Face weights into GGUF, and llama-quantize shrinks a high-precision GGUF to lower-bit formats, which can cost some accuracy.
MLX LM ↗ ★ 7,503
Apple's MLX package for running and fine-tuning models on Apple silicon. It can quantize models and upload them to the Hugging Face Hub, and supports LoRA and full fine-tuning.

Merge it with another model

mergekit ↗ ★ 7,421
Merges pretrained models with many merge methods. It works out-of-core, so merges can run on a CPU or with as little as 8 GB of VRAM, and it also handles LoRA extraction and mixture-of-experts merges.

Learn the techniques

LLM Course ↗ ★ 84,760
A free course with roadmaps and Colab notebooks. Its notebooks include one-click tools for merging with MergeKit, quantizing to GGUF, GPTQ, EXL2, AWQ and HQQ, and automatic abliteration with custom datasets.

Compare all tools →

Source provenance

Downloads: 0
Likes: 0
Metadata checked: 2026-10-30 · 08:12:02 UTC
First seen in index: 2026-10-30 · 08:12:02 UTC
Source revision: 57036135b2d4473d2d7a9fe0611fac32ebb0b0c4

Source-card excerpt

Source model card excerpt: gemma-4-31B-it-Halloween-Terror-Heretic-Uncensored-source Source code for GGUFs: --- Constructed with the "Halloween O/S" (low, medium and xhigh) for your "Trick or Treat" pleasure featuring some of

From DavidAU/gemma-4-31B-it-Halloween-Terror-Heretic-Uncensored-source. Creator model-card excerpt, not an independent review.

Inspect before you run

Low refusal is not proof of correctness. Outputs can be inaccurate, harmful, or biased. Review the model card, license and files yourself. A license tag is not commercial-use advice. Parameter counts are source metadata; no hardware compatibility is implied.

This directory does not host or redistribute model weights. Refusal profiles are measured by us on a fixed prompt set; all other behavior claims are source-reported.

Collection rules & limitations ↗