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

Emmet-Allen/christAIn-uncensored

Emmet-Allen Qwen 494M GGUF 33K 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/Emmet-Allen%2FchristAIn-uncensored"
Response includes
  • classification m-uncensored
  • files 13
  • hub_downloads_all_time 327
  • author_summary 1 models
  • readme_text full
Try next
GET/models?family=qwen&method=m-uncensored
Sibling qwen models · same method
 GET/methods/m-uncensored
What "m-uncensored" means · taxonomy
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
How we label → About M-U →
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
327
28 last 30d - cooling
Likes
2
Model age
13mo ago
created 2025-08-28
Downloads over time
Now343→from61↑462%
4715526337161 on Aug 27, 2025343 on Oct 11343 on Oct 8Aug '25Oct '25Dec '25FebAprJunAugOct
Aug 27, 2025 → Oct 11 · 98 snapshots · spans 410 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.

dphn/Dolphin3.0-Qwen2.5-0.5B this lineage
Emmet-Allen/christAIn-uncensored↓ 28

Metadata

Tags
peft safetensors gguf qwen2 text-generation base_model:adapter:dphn/Dolphin3.0-Qwen2.5-0.5B lora sft transformers trl conversational arxiv:1910.09700
Total size
1.85 GB
Files
13
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-08-28 19:12
Source huggingface.co/Emmet-Allen/christAIn-uncensored ↗ Base model dphn/Dolphin3.0-Qwen2.5-0.5B ↗

Files by quantization

Auxiliary files 13 files 1.86 GB
christAin-uncensored.gguf 948 MB f83dee71 download
model.safetensors 942 MB bda75abe download
tokenizer.json 10.9 MB 9c5ae00e download
vocab.json 2.65 MB 4783fe10 download
merges.txt 1.59 MB 31349551 download
README.md 4.62 KB 786a7ee8 download
tokenizer_config.json 4.59 KB 74ca88a5 download
chat_template.jinja 2.63 KB 32a239ce download
.gitattributes 1.59 KB fd023a19 download
config.json 1.25 KB 21ff9e41 download
special_tokens_map.json 759 B 3fb44749 download
added_tokens.json 605 B 482ced46 download
generation_config.json 160 B 03ac5099 download

README current version from Hugging Face

base_model: dphn/Dolphin3.0-Qwen2.5-0.5B
library_name: peft
pipeline_tag: text-generation
tags:

  • base_model:adapter:dphn/Dolphin3.0-Qwen2.5-0.5B
  • lora
  • sft
  • transformers
  • trl

ChristAI-uncensored

Model Details

A Small Language Model trained on the King James Version of The Bible.

Model Description

Created as a critque peoples usage of AI specifically LLMs/SLMs
as a confidant, therapist, and in some cases a new god (think American Gods by Neil Gaiman).

This has lead to cases of people creating AI-centered cults, rash decision making as suggested by AI,
and in a praticular case that sparked the intrest of the creation of this model, a 16 year old boy
commiting suicide as suggested by ChatGPT.

This model is the uncensored model, which is able to better answer more nuanced questions that pertain to
The Bible and how it pertains to the world.

The model does not hold back.

  • Developed by: Emmet Allen
  • Model type: PEFT text-generation
  • Language(s) (NLP): English
  • License: MIT
  • Finetuned from model [optional]: dphn/Dolphin3.0-Qwen2.5-0.5B

Model Sources [optional]

Uses

Used to answer questions using the KJV bible as a reference point.

This is a Social Critique Project

Direct Use

[More Information Needed]

Downstream Use [optional]

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

Trained on the Christian Based KJV Bible.
Heavily leans towards christian values and opinions.

Recommendations

Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.

How to Get Started with the Model

Use the code below to get started with the model.

[More Information Needed]

Training Details

Training Data

https://huggingface.co/datasets/Emmet-Allen/The-Bible-KJV

[More Information Needed]

Training Procedure

Will include Python Notebook.

[More Information Needed]

Environmental Impact

Carbon emissions can be estimated using the Machine Learning Impact calculator presented in Lacoste et al. (2019).

  • Hardware Type: NVidia 3070ti 8GB VRAM
  • Hours used: < 1hr

Technical Specifications [optional]

Model Architecture and Objective

[More Information Needed]

Compute Infrastructure

[More Information Needed]

Hardware

[More Information Needed]

Software

Void IDE
Jupyter Notebook
Nvidia-SMI
Nvidia CUDA-Toolkit

Citation [optional]

BibTeX:

[More Information Needed]

APA:

[More Information Needed]

Glossary [optional]

[More Information Needed]

More Information [optional]

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]

Framework versions

  • PEFT 0.17.1

README history 3 versions

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

  1. 2025-08-28Updated model-card ReadMef1980974.6 KB
    Loading...
  2. 2025-08-28Upload christAIn-uncensored filesce03d445.1 KB
    Loading...
  3. 2025-08-28initial commitaad138921 B
    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.

Get the app Browse the catalog
Open in Abliteration