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

nkpz/T3Q-qwen2.5-14b-v1.0-e3-Uncensored-DeLMAT

nkpz Qwen 15B
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/nkpz%2FT3Q-qwen2.5-14b-v1.0-e3-Uncensored-DeLMAT"
Response includes
  • classification m-uncensored
  • files 16
  • hub_downloads_all_time 260
  • author_summary 18 models
  • readme_text full
Try next
GET/models?author=nkpz
All 18 models by nkpz
 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
260
14 last 30d - cooling
Likes
4
Descendants
2
in 2 direct forks
Model age
19mo ago
created 2025-03-16
Downloads over time
Now265→from5↑5,200%
0971942915 on Mar 12, 2025265 on Oct 11265 on Oct 5Mar '25Jun '25Sep '25Dec '25MarJunSep
Mar 12, 2025 → Oct 11 · 122 snapshots · spans 578 days

Genealogy 2 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.

JungZoona/T3Q-qwen2.5-14b-v1.0-e3 this lineage
nkpz/T3Q-qwen2.5-14b-v1.0-e3-Uncensored-DeLMAT↓ 14 2 forks
mradermacher/T3Q-qwen2.5-14b-v1.0-e3-Uncensored-DeLMAT-i1-GGUF↓ 841
mradermacher/T3Q-qwen2.5-14b-v1.0-e3-Uncensored-DeLMAT-GGUF↓ 288

Metadata

License
apache-2.0
Tags
safetensors qwen2 base_model:JungZoona/T3Q-qwen2.5-14b-v1.0-e3 base_model:finetune:JungZoona/T3Q-qwen2.5-14b-v1.0-e3 license:apache-2.0 region:us

Related

Other by nkpz
llama2-22b-chat-wizard-uncensored 68 open_llama_7b_qlora_uncensored-gptq 23 Llama-3.1-8B-Instruct-Uncensored-DeLMAT 17 Fino1-8B-Uncensored-DeLMAT 16 Qwen2.5-Dyanka-7B-Preview-Uncensored-DeLMAT 16
Total size
27.5 GB
Files
16
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-03-16 21:40
Source huggingface.co/nkpz/T3Q-qwen2.5-14b-v1.0-e3-Uncensored-DeLMAT ↗ Base model JungZoona/T3Q-qwen2.5-14b-v1.0-e3 ↗

Files by quantization

Auxiliary files 16 files 27.5 GB
model-00001-of-00006.safetensors 4.64 GB 4ee44f06 download
model-00003-of-00006.safetensors 4.61 GB b6663876 download
model-00004-of-00006.safetensors 4.61 GB a7ad508e download
model-00005-of-00006.safetensors 4.61 GB 528654b4 download
model-00002-of-00006.safetensors 4.61 GB d2a710db download
model-00006-of-00006.safetensors 4.41 GB c23f5aee download
tokenizer.json 10.9 MB 9c5ae00e download
vocab.json 2.65 MB 4783fe10 download
model.safetensors.index.json 46.4 KB 0e9b5353 download
tokenizer_config.json 7.08 KB 188bc228 download
.gitattributes 1.53 KB 52373fe2 download
README.md 832 B 35ded25f download
config.json 832 B acd28c3d download
added_tokens.json 605 B 482ced46 download
special_tokens_map.json 496 B aa59b333 download
generation_config.json 248 B 2188e564 download

README current version from Hugging Face

license: apache-2.0
base_model:

  • JungZoona/T3Q-qwen2.5-14b-v1.0-e3

Decensored using a custom training script guided by activations, similar to ablation/"abliteration" scripts but not exactly the same approach.

Original model is #14 ranked on Open LLM Leaderboard

The training script is released under the MIT license: https://github.com/nkpz/DeLMAT - This model was built using an upcoming development version

This is overtrained toward acceptance, and it overuses the words like "absolutely" and "sure". I don't think I'd recommend it for creative writing for this reason, but it's decent for question answering and getting it to say bizarre things. I almost decided not to release this because it's so unbalanced, but I think there's something kind of fun and interesting about always getting an affirmative response.

README history 2 versions

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

  1. 2025-03-16Update README.mdfd8b4d2832 B
    Loading...
  2. 2025-03-16initial commitb25cb3428 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