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

jfiekdjdk/UncensoredLM-DeepSeek-R1-Distill-Qwen-14B-4.25bpw-h6-exl2

jfiekdjdk Qwen 14B
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/jfiekdjdk%2FUncensoredLM-DeepSeek-R1-Distill-Qwen-14B-4.25bpw-h6-exl2"
Response includes
  • classification m-uncensored
  • files 10
  • hub_downloads_all_time 166
  • author_summary 5 models
  • readme_text full
Try next
GET/models?author=jfiekdjdk
All 5 models by jfiekdjdk
 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
166
25 last 30d - stable
Likes
3
Model age
20mo ago
created 2025-02-02
Downloads over time
Now180→from2↑8,900%
0661321982 on Jan 29, 2025180 on Oct 11Jan '25Apr '25Jul '25Oct '25JanAprJulOct
Jan 29, 2025 → Oct 11 · 128 snapshots · spans 620 days

Metadata

License
apache-2.0
Tags
safetensors qwen2 license:apache-2.0 exl2 region:us

Related

Other by jfiekdjdk
Qwen3-8B-abliterated-Q5_K_M-GGUF 619 GLM-Z1-9B-0414-abliterated-Q6_K-GGUF 35 GLM-4-9B-0414-abliterated-Q6_K-GGUF 30 Qwen2.5-14B-Instruct-abliterated-4.0bpw-h6-exl2 19
Total size
8.29 GB
Files
10
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-02-02 13:44
Source huggingface.co/jfiekdjdk/UncensoredLM-DeepSeek-R1-Distill-Qwen-14B-4.25bpw-h6-exl2 ↗

Files by quantization

Auxiliary files 10 files 8.29 GB
output-00001-of-00002.safetensors 7.72 GB 985b25cc download
output-00002-of-00002.safetensors 585 MB fa8be26e download
tokenizer.json 6.71 MB a3465099 download
UAI_Thinking.webp 374 KB 9f9115d1 download
model.safetensors.index.json 42.3 KB 8819db3d download
h5dTflRHYMbGq3RXm9a61yz4io.avif 12.9 KB 28b9db66 download
tokenizer_config.json 2.99 KB 9a63ccfe download
.gitattributes 1.54 KB 988a2f01 download
config.json 1.05 KB 1f37055c download
README.md 1001 B de3113b0 download

README current version from Hugging Face

license: apache-2.0

An UncensoredLLM with Reasoning, what more could you want?

  • Note this is an experimental preview and we will continue improving based on feedback, so please good and bad feedback welcome. Leave it in the Community Comments and I will address your feedback asap.
    UAI

  • Refusal Alignment is pretty clear where we draw the line:
    UAI

You might be asking yourself: Why Uncensored AI?
UAI
Prompt Template the model is trained on:

"instruction,input,output": "The following user query requires an answer that is derived from the context given. It is imperative that the answer is not based on external knowledge or assumptions. Analyze the context thoroughly to extract the necessary information that will form the basis of a clear and accurate answer.<｜User｜>\n%instruction%\n%input%\n<｜Assistant｜>\n%output%",

We just launched our beta, LOOK INTO IT at https://uncensored.ai

README history 1 version

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

  1. 2025-02-02Upload folder using huggingface_hubdb4997b1001 B
    Loading...

Discussions 1 thread

  1. 2025-02-02Please offer a ollama download way.closed2 💬#1
    Loading...

Continue on Hugging Face →

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