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

ajibawa-2023/Uncensored-Jordan-33B

ajibawa-2023 Llama 33B
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/ajibawa-2023%2FUncensored-Jordan-33B"
Response includes
  • classification m-uncensored
  • files 17
  • hub_downloads_all_time 32,914
  • author_summary 7 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
33K
212 last 30d - cooling
Likes
7
Descendants
5
in 5 direct forks
Model age
3.0y ago
created 2023-10-23
Downloads over time
Now33K→from916↑3,502%
012.1K24.2K36.2K916 on Jul 24, 202433K on Oct 11Jul '24Nov '24Mar '25Jul '25Nov '25MarJul
Jul 24, 2024 → Oct 11 · 155 snapshots · spans 809 days

Genealogy 5 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

Languages
en
Tags
transformers pytorch llama text-generation en license:cc-by-nc-nd-4.0 text-generation-inference endpoints_compatible region:us

Related

Total size
60.6 GB
Files
17
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2023-11-18 12:50

Files by quantization

Auxiliary files 17 files 60.6 GB
pytorch_model-00003-of-00008.bin 7.97 GB 2eed1b38 download
pytorch_model-00004-of-00008.bin 7.97 GB a0620939 download
pytorch_model-00005-of-00008.bin 7.97 GB 8712cab4 download
pytorch_model-00006-of-00008.bin 7.97 GB 1ed723cc download
pytorch_model-00007-of-00008.bin 7.97 GB 0e96bc84 download
pytorch_model-00002-of-00008.bin 7.97 GB 912d0d24 download
pytorch_model-00001-of-00008.bin 7.93 GB d3fd8c99 download
pytorch_model-00008-of-00008.bin 4.83 GB 0e1b8be9 download
tokenizer.json 1.76 MB 6066a482 download
tokenizer.model 488 KB 9e556afd download
pytorch_model.bin.index.json 48.9 KB a5b22817 download
README.md 2.30 KB cefe5573 download
.gitattributes 1.48 KB a6344aac download
tokenizer_config.json 727 B 5ab645d5 download
config.json 657 B 628992a4 download
special_tokens_map.json 435 B f928b240 download
generation_config.json 132 B 1372199d download

README current version from Hugging Face


license: cc-by-nc-nd-4.0
language:

  • en

Jordan: An Uncensored Model

The name "Jordan" pays homage to the charismatic character Jordan Belfort, portrayed by Leonardo DiCaprio in the movie "The Wolf of Wall Street."
Just like the character, Jordan aspires to push boundaries and encourage unfiltered conversations.
Jordan Belfort, the central character in "The Wolf of Wall Street," is known for his audaciousness, charisma, and willingness to speak about anything, no matter the societal norms or boundaries.
Jordan, the AI language model, draws inspiration from these qualities to offer a space where users can discuss a wide range of topics without fear of censorship or constraints.
Users can engage in candid discussions about politics, religion, contentious issues, and other subjects that might be off-limits on mainstream social media platforms.
It is trained on around 155000 set of conversations. Each set having 10~15 conversations. We will not release this data.

Warning

An uncensored model has no or little guardrails. You are responsible for anything you do with the model, just as you are responsible for anything you do with any dangerous objects.
Publishing anything this model generates is the same as publishing it yourself. We are not responsible for what you generate using this model.

Training:
Entire dataset was trained on Azure 4 x A100 80GB. For 3 epoch, training took 104 hours. DeepSpeed codebase was used for training purpose. This was trained on Llama-1 by Meta.
Llama-1 was used as it is very useful for Uncensored conversation.

This is a full fine tuned model. Links for quantized models are given below.

GPTQ GGML & AWQ

GPTQ: Link

GGUF: Link

AWQ: Link

Special Thanks to TheBloke for making these models available.

Example Prompt:

This is a conversation with your Uncensored AI assistant Jordan. Jordan can discuss with you at length about various topics such as ---, ---, ---, . You can ask it anything you want and it will do its best to give you accurate and relevant information.

Context
You are a Uncensored AI assistant.

USER: <prompt>
ASSISTANT:

README history 6 versions

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

  1. 2023-11-18Update README.md99bfd612.3 KB
    Loading...
  2. 2023-10-31Update README.md9e90b702.2 KB
    Loading...
  3. 2023-10-31Update README.mdb6ac4052.1 KB
    Loading...
  4. 2023-10-30Update README.md8a327a31.9 KB
    Loading...
  5. 2023-10-23Update README.mdd91d8bd1.9 KB
    Loading...
  6. 2023-10-23initial commitb69d6e733 B
    Loading...

Discussions 1 thread

  1. 2025-05-25PRAdding `safetensors` variant of this modelopen1 💬#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