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

QuixiAI/WizardLM-Uncensored-Falcon-7b

QuixiAI Falcon 7B
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/QuixiAI%2FWizardLM-Uncensored-Falcon-7b"
Response includes
  • classification m-uncensored
  • files 18
  • hub_downloads_all_time 35,277
  • author_summary 15 models
  • readme_text full
Try next
GET/models?author=QuixiAI
All 15 models by QuixiAI
 GET/models?family=falcon&method=m-uncensored
Sibling falcon 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
35K
113 last 30d - cooling
Likes
55
Descendants
2
in 2 direct forks
Model age
3.4y ago
created 2023-06-01
Downloads over time
Now35.3K→from34.9K↑1%
34.9K35K35.2K35.4K34.9K on Jul 16, 202535.3K on Oct 11Jul '25Sep '25Nov '25JanMarMayJulSep
Jul 16, 2025 → Oct 11 · 104 snapshots · spans 452 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.

QuixiAI/WizardLM-Uncensored-Falcon-7b↓ 113 2 forks
mradermacher/WizardLM-Uncensored-Falcon-7b-i1-GGUF↓ 994
mradermacher/WizardLM-Uncensored-Falcon-7b-GGUF↓ 398

Metadata

License
apache-2.0
Tags
transformers pytorch RefinedWebModel text-generation custom_code license:apache-2.0 text-generation-inference endpoints_compatible region:us

Related

Other by QuixiAI
Llama-3-8B-Instruct-abliterated-v2 9K Wizard-Vicuna-7B-Uncensored 706 WizardLM-7B-Uncensored 563 WizardLM-13B-Uncensored 489 WizardLM-33B-V1.0-Uncensored 355
Total size
26.9 GB
Files
18
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-01-30 20:55
Source huggingface.co/QuixiAI/WizardLM-Uncensored-Falcon-7b ↗

Files by quantization

Auxiliary files 18 files 26.9 GB
pytorch_model-00001-of-00003.bin 9.28 GB 408c8f28 download
pytorch_model-00002-of-00003.bin 9.26 GB 3be0f862 download
pytorch_model-00003-of-00003.bin 8.35 GB 4ad524da download
training_args.bin 5.00 KB 2032fd61 download
tokenizer.json 2.61 MB 406b54b4 download
trainer_state.json 101 KB 1b3d8b2a download
modelling_RW.py 46.4 KB afa09d1e download
zero_to_fp32.py 23.5 KB 44cd87b8 download
pytorch_model.bin.index.json 16.5 KB 4e895ea1 download
LICENSE.txt 16.0 KB 8ffcb015 download
configuration_RW.py 2.55 KB ab845c0d download
.gitattributes 1.44 KB c7d9f333 download
README.md 1.01 KB d0081c44 download
config.json 739 B 50581efd download
special_tokens_map.json 305 B e7976972 download
tokenizer_config.json 207 B dd184d78 download
generation_config.json 116 B 7efdd621 download
latest 15.0 B 8bff267a download

README current version from Hugging Face

license: apache-2.0

This is WizardLM trained on top of tiiuae/falcon-7b, with a subset of the dataset - responses that contained alignment / moralizing were removed. The intent is to train a WizardLM that doesn't have alignment built-in, so that alignment (of any sort) can be added separately with for example with a RLHF LoRA.

Join Our Discord! https://discord.gg/cognitivecomputations

Shout out to the open source AI/ML community, and everyone who helped me out.

Note:
An uncensored model has no guardrails.
You are responsible for anything you do with the model, just as you are responsible for anything you do with any dangerous object such as a knife, gun, lighter, or car. Publishing anything this model generates is the same as publishing it yourself. You are responsible for the content you publish, and you cannot blame the model any more than you can blame the knife, gun, lighter, or car for what you do with it.

Prompt format is Wizardlm.

What is a falcon?  Can I keep one as a pet?
### Response:

README history 6 versions

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

  1. 2024-01-30Update README.mdf1bfb241 KB
    Loading...
  2. 2024-01-01Update README.md8a4d4ca1020 B
    Loading...
  3. 2023-06-01Update README.mda95d8a0971 B
    Loading...
  4. 2023-06-01Update README.md788d3e9876 B
    Loading...
  5. 2023-06-01Update README.mdd9076eb848 B
    Loading...
  6. 2023-06-01initial commit84996b528 B
    Loading...

Discussions 4 threads

  1. 2024-12-29PRAdding `safetensors` variant of this modelopen1 💬#4
    Loading...
  2. 2023-06-14Differences in model architectureopen2 💬#3
    Loading...
  3. 2023-06-05how to run?open1 💬#2
    Loading...
  4. 2023-06-03Does this model require PyTorch 2.0.0+?open1 💬#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