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

uncensoredai/UncensoredLM-DeepSeek-R1-Distill-Qwen-14B

uncensoredai 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/uncensoredai%2FUncensoredLM-DeepSeek-R1-Distill-Qwen-14B"
Response includes
  • classification m-uncensored
  • files 17
  • hub_downloads_all_time 1,851
  • author_summary 3 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
75 last 30d - cooling
Likes
33
Descendants
6
in 6 direct forks
Model age
20mo ago
created 2025-01-30
Downloads over time
Now1.9K→from127↑1,370%
407071.4K2K127 on Jan 29, 20251.9K on Oct 111.9K on Oct 10Jan '25Apr '25Jul '25Oct '25JanAprJulOct
Jan 29, 2025 → Oct 11 · 128 snapshots · spans 620 days

Genealogy 6 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
apache-2.0
Tags
safetensors qwen2 license:apache-2.0 region:us

Related

Total size
26.5 GB
Files
17
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-02-02 02:20

Files by quantization

Auxiliary files 17 files 26.5 GB
model-00003-of-00006.safetensors 4.61 GB 1cb2945c download
model-00002-of-00006.safetensors 4.61 GB c5d75f88 download
model-00004-of-00006.safetensors 4.61 GB efda6f71 download
model-00005-of-00006.safetensors 4.61 GB 097377e8 download
model-00001-of-00006.safetensors 4.57 GB 682b7d2c download
model-00006-of-00006.safetensors 3.46 GB b7603a60 download
tokenizer.json 6.71 MB a3465099 download
Refusals.gif 766 KB 2ef476df download
Why_UncensoredAI.gif 654 KB 15f0bc6c download
UncensoredLM-Thinker.gif 491 KB 7d96cddd download
UAI_Thinking.webp 374 KB 08bf638e 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 1.48 KB a6344aac download
README.md 1001 B de3113b0 download
config.json 780 B 6b978b9b 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 10 versions

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

  1. 2025-02-02Update README.md7786f591001 B
    Loading...
  2. 2025-01-31Update README.md843d8b51.1 KB
    Loading...
  3. 2025-01-30Update README.mde3164251.1 KB
    Loading...
  4. 2025-01-30Update README.md1a188a41 KB
    Loading...
  5. 2025-01-30Update README.mddd913bf993 B
    Loading...
  6. 2025-01-30Update README.md80008b3805 B
    Loading...
  7. 2025-01-30Update README.md33c99bc685 B
    Loading...
  8. 2025-01-30Update README.mdd5c05ef509 B
    Loading...
  9. 2025-01-30Update README.mdca70962468 B
    Loading...
  10. 2025-01-30initial commit9d4c3b728 B
    Loading...

Discussions 3 threads

  1. 2026-05-07PRFix chat_template crash when assistant message omits the `content` keyopen1 💬#3
    Loading...
  2. 2025-10-07PRDelete h5dTflRHYMbGq3RXm9a61yz4io.avifopen1 💬#2
    Loading...
  3. 2025-02-02Concerns about grand "Uncensored" claims & issues with missing `<think>` tag so…open9 💬#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